A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis
São Carlos Institute of Physics, University of São Paulo（圣保罗大学圣卡洛斯物理学院）；Institute of Mathematics and Computer Sciences, University of São Paulo（圣保罗大学数学与计算机科学研究所）；Institute of Biosciences, Humanities and Exact Sciences, São Paulo State University（圣保罗州立大学生物科学、人文与精确科学研究所）；Ghent University（根特大学）
Leonardo Scabini, Andre Sacilotti, Kallil M. Zielinski, Lucas C. Ribas, Bernard De Baets, Odemir M. Bruno
Texture, a significant visual attribute in images, has been extensively investigated across various image recognition applications. Convolutional Neural Networks (CNNs), which have been successful in many computer vision tasks, are currently among the best texture analysis approaches. On the other hand, Vision Transformers (ViTs) have been surpassing the performance of CNNs on tasks such as object recognition, causing a paradigm shift in the field. However, ViTs have so far not been scrutinized for texture recognition, hindering a proper appreciation of their potential in this specific setting. For this reason, this work explores various pre-trained ViT architectures when transferred to tasks that rely on textures. We review 21 different ViT variants and perform an extensive evaluation and comparison with CNNs and hand-engineered models on several tasks, such as assessing robustness to changes in texture rotation, scale, and illumination, and distinguishing color textures, material textures, and texture attributes. The goal is to understand the potential and differences among these models when directly applied to texture recognition, using pre-trained ViTs primarily for feature extraction and employing linear classifiers for evaluation. We also evaluate their efficiency, which is one of the main drawbacks in contrast to other methods. Our results show that ViTs generally outperform both CNNs and hand-engineered models, especially when using stronger pre-training and tasks involving in-the-wild textures (images from the internet). We highlight the following promising models: ViT-B with DINO pre-training, BeiTv2, and the Swin architecture, as well as the EfficientFormer as a low-cost alternative. In terms of efficiency, although having a higher number of GFLOPs and parameters, ViT-B and BeiT(v2) can achieve a lower feature extraction time on GPUs compared to ResNet50.
This paper aims to compare between four different types of feature extraction approaches in terms of texture segmentation. The feature extraction methods that were used for segmentation are Gabor filters (GF), Gaussian Markov random fields (GMRF), run-length matrix (RLM) and co-occurrence matrix (GLCM). It was shown that the GF performed best in terms of quality of segmentation while the GLCM localises the texture boundaries better as compared to the other methods.
In this paper, we examine several typical texture attributes developed in the image processing community in recent years with respect to their capability of characterizing a migrated seismic volume. These attributes are generated in either frequency or space domain, including steerable pyramid, curvelet, local binary pattern, and local radius index. The comparative study is performed within an image retrieval framework. We evaluate these attributes in terms of retrieval accuracy. It is our hope that this comparative study will help acquaint the seismic interpretation community with the many av…
Avinashilingam Institute for Home Science and Higher Education for Women（阿维纳希林加姆家政与高等教育女子学院）
Texture segmentation is the process of partitioning an image into regions with different textures containing a similar group of pixels. Detecting the discontinuity of the filter's output and their statistical properties help in segmenting and classifying a given image with different texture regions. In this proposed paper, chili x-ray image texture segmentation is performed by using Gabor filter. The texture segmented result obtained from Gabor filter fed into three texture filters, namely Entropy, Standard Deviation and Range filter. After performing texture analysis, features can be extracte…
Georgia Institute of Technology（佐治亚理工学院）；King Fahd University of Petroleum and Minerals（法赫德国王石油与矿业大学）；Center for Energy and Geo Processing（能源与地理处理中心）
In this paper, we explore how to computationally characterize subsurface geological structures presented in seismic volumes using texture attributes. For this purpose, we conduct a comparative study of typical texture attributes presented in the image processing literature. We focus on spatial attributes in this study and examine them in a new application for seismic interpretation, i.e., seismic volume labeling. For this application, a data volume is automatically segmented into various structures, each assigned with its corresponding label. If the labels are assigned with reasonable accuracy…
Research into the visual cortex and general neural information processing has led to various attempts to integrate pulse computation schemes in image analysis systems. Of interest is especially the robustness of representing an analogue signal in the phase or duration of a pulsed, quasi-digital signal, as well as the possibility of direct digital interaction, i.e. computation, among these signals. Such a computation can also achieve information compaction for subsequent processing stages. By using a pulse order encoding scheme motivated by dendritic pulse interaction, we will show that a power…
Edges characterize boundaries and are therefore a problem of practical importance in remote sensing.In this paper a comparative study of various edge detection techniques and band wise analysis of these algorithms in the context of object extraction with regard to remote sensing satellite images from the Indian Remote Sensing Satellite (IRS) sensors LISS 3, LISS 4 and Cartosat1 as well as Google Earth is presented.
Texture-based classification solutions have proven their significance in many domains, from industrial inspections to health-related applications. New methods have been developed based on texture feature learning and CNN-based architectures to address computer vision use cases for images with rich texture-based features. In recent years, architectures solving texture-based classification problems and demonstrating state-of-the-art results have emerged. Yet, one limitation of these approaches is that they cannot claim to be suitable for all types of image texture patterns. Each technique has an…
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Tencent America（腾讯美国）；Advanced Institute of Information Technology, Peking University（北京大学高等信息科学技术研究院）
We deal with the controllable person image synthesis task which aims to re-render a human from a reference image with explicit control over body pose and appearance. Observing that person images are highly structured, we propose to generate desired images by extracting and distributing semantic entities of reference images. To achieve this goal, a neural texture extraction and distribution operation based on double attention is described. This operation first extracts semantic neural textures from reference feature maps. Then, it distributes the extracted neural textures according to the spati…
Texture analysis and classification are some of the problems which have been paid much attention by image processing scientists since late 80s. If texture analysis is done accurately, it can be used in many cases such as object tracking, visual pattern recognition, and face recognition.Since now, so many methods are offered to solve this problem. Against their technical differences, all of them used same popular databases to evaluate their performance such asBrodatz or Outex, which may be made their performance biased on these databases. In this paper, an approach is proposed to collect more e…
New Horizon College of Engineering（新视野工程学院）；Government Engineering College（政府工程学院）；University of Mysore（迈索尔大学）
Periodicity of a texture is one of the important visual characteristics and is often used as a measure for textural discrimination at the structural level. Knowledge about periodicity of a texture is very essential in the field of texture synthesis and texture compression and also in the design of frieze and wall papers. In this paper, we propose a method of periodicity extraction from noisy images based on superposition of distance matching function (DMF) and wavelet decomposition without de-noising the test images. Overall DMFs are subjected to single-level Haar wavelet decomposition to obta…
University of São Paulo（圣保罗大学）；University of Campinas（坎皮纳斯大学）
Convolutional neural networks have shown successful results in image classification achieving real-time results superior to the human level. However, texture images still pose some challenge to these models due, for example, to the limited availability of data for training in several problems where these images appear, high inter-class similarity, the absence of a global viewpoint of the object represented, and others. In this context, the present paper is focused on improving the accuracy of convolutional neural networks in texture classification. This is done by extracting features from mult…
Researches of analysis and parsing around façades to enrich the 3D feature of façade models by semantic information raised some attention in the community, whose main idea is to generate higher resolution components with similar shapes and textures to increase the overall resolution at the expense of reconstruction accuracy. While this approach works well for components like windows and doors, there is no solution for façade background at present. In this paper, we introduce the concept of representative region texture, which can be used in the above modeling approach by tiling the representat…
Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究科）；Biometrics Research Laboratories, NEC Corporation（NEC公司生物识别研究所）
Although most fingerprint matching methods utilize minutia points and/or texture of fingerprint images as fingerprint features, the frequency spectrum is also a useful feature since a fingerprint is composed of ridge patterns with its inherent frequency band. We propose a novel CNN-based method for extracting fingerprint features from texture, minutiae, and frequency spectrum. In order to extract effective texture features from local regions around the minutiae, the minutia attention module is introduced to the proposed method. We also propose new data augmentation methods, which takes into ac…
Text extraction is an important problem in image processing with applications from optical character recognition to autonomous driving. Most of the traditional text segmentation algorithms consider separating text from a simple background (which usually has a different color from texts). In this work we consider separating texts from a textured background, that has similar color to texts. We look at this problem from a signal decomposition perspective, and consider a more realistic scenario where signal components are overlaid on top of each other (instead of adding together). When the signals…
In this paper we use machine learning to study the application of Local Tchebichef Moments (LTM) to the problem of texture classification. The original LTM method was proposed by Mukundan (2014). The LTM method can be used for texture analysis in many different ways, either using the moment values directly, or more simply creating a relationship between the moment values of different orders, producing a histogram similar to those of Local Binary Pattern (LBP) based methods. The original method was not fully tested with large datasets, and there are several parameters that should be characteris…
SOM is a type of unsupervised learning where the goal is to discover some underlying structure of the data. In this paper, a new extraction method based on the main idea of Concurrent Self-Organizing Maps (CSOM), representing a winner-takes-all collection of small SOM networks is proposed. Each SOM of the system is trained individually to provide best results for one class only. The experiments confirm that the proposed features based CSOM is capable to represent image content better than extracted features based on a single big SOM and these proposed features improve the final decision of the…
University of São Paulo（圣保罗大学）；ENSTA-ParisTech（巴黎高等先进技术学校）；Université de Paris-Saclay（巴黎-萨克雷大学）
To recognize textures many methods have been developed along the years. However, texture datasets may be hard to be classified due to artefacts such as a variety of scale, illumination and noise. This paper proposes the application of binary distance transform on the original dataset to add information to texture representation and consequently improve recognition. Texture images, usually in grayscale, suffers a binarization prior to distance transform and one of the resulted images are combined with original texture to improve the amount of information. Four datasets are used to evaluate our …
Texture is one of the most important properties of visual surface that helps in discriminating one object from another or an object from background. The self-organizing map (SOM) is an excellent tool in exploratory phase of data mining. It projects its input space on prototypes of a low-dimensional regular grid that can be effectively utilized to visualize and explore properties of the data. This paper proposes an enhancement extraction method for accurate extracting features for efficient image representation it based on SOM neural network. In this approach, we apply three different partition…
The advent of large scale multimedia databases has led to great challenges in content-based image retrieval (CBIR). Even though CBIR is considered an emerging field of research, however it constitutes a strong background for new methodologies and systems implementations. Therefore, many research contributions are focusing on techniques enabling higher image retrieval accuracy while preserving low level of computational complexity. Image retrieval based on texture features is receiving special attention because of the omnipresence of this visual feature in most real-world images. This paper hig…
Brunel University London（布鲁内尔大学伦敦分校）；Ecole Centrale de Lyon（里昂中央理工学院）；Xi’an Jiaotong University（西安交通大学）
Meaningful facial parts can convey key cues for both facial action unit detection and expression prediction. Textured 3D face scan can provide both detailed 3D geometric shape and 2D texture appearance cues of the face which are beneficial for Facial Expression Recognition (FER). However, accurate facial parts extraction as well as their fusion are challenging tasks. In this paper, a novel system for 3D FER is designed based on accurate facial parts extraction and deep feature fusion of facial parts. In particular, each textured 3D face scan is firstly represented as a 2D texture map and a dep…
In this paper, we present a novel approach for image retrieval based on extraction of low level features using techniques such as Directional Binary Code, Haar Wavelet transform and Histogram of Oriented Gradients. The DBC texture descriptor captures the spatial relationship between any pair of neighbourhood pixels in a local region along a given direction, while Local Binary Patterns descriptor considers the relationship between a given pixel and its surrounding neighbours. Therefore, DBC captures more spatial information than LBP and its variants, also it can extract more edge information th…
Feature extraction is a key step in image processing for pattern recognition and machine learning processes. Its purpose lies in reducing the dimensionality of the input data through the computing of features which accurately describe the original information. In this article, a new feature extraction method based on Discrete Modal Decomposition (DMD) is introduced, to extend the group of space and frequency based features. These new features are called modal features. Initially aiming to decompose a signal into a modal basis built from a vibration mechanics problem, the DMD projection is appl…
NICTA（澳大利亚国家信息与通信技术研究院）；The University of Queensland（昆士兰大学）
This paper presents a survey and a comparative evaluation of recent techniques for moving cast shadow detection. We identify shadow removal as a critical step for improving object detection and tracking. The survey covers methods published during the last decade, and places them in a feature-based taxonomy comprised of four categories: chromacity, physical, geometry and textures. A selection of prominent methods across the categories is compared in terms of quantitative performance measures (shadow detection and discrimination rates, colour desaturation) as well as qualitative observations. Fu…
The aim of a Content-Based Image Retrieval (CBIR) system, also known as Query by Image Content (QBIC), is to help users to retrieve relevant images based on their contents. CBIR technologies provide a method to find images in large databases by using unique descriptors from a trained image. The image descriptors include texture, color, intensity and shape of the object inside an image. Several feature-extraction techniques viz., Average RGB, Color Moments, Co-occurrence, Local Color Histogram, Global Color Histogram and Geometric Moment have been critically compared in this paper. However, ind…
Where data is available, it is desirable in geostatistical modelling to make use of additional covariates, for example terrain data, in order to improve prediction accuracy in the modelling task. While elevation itself may be important, additional explanatory power for any given problem can be sought (but not necessarily found) by filtering digital elevation models to extract higher-order derivatives such as slope angles, curvatures, and roughness. In essence, it would be beneficial to extract as much task-relevant information as possible from the elevation grid. However, given the complexitie…
Department of Computer Science and Engineering（计算机科学与工程系）；Michigan State University（密歇根州立大学）；East Lansing（东兰辛（城市名，非机构））；Michigan 48824（密歇根州 48824（邮编，非机构））
We propose a texture template approach, consisting of a set of virtual minutiae, to improve the overall latent fingerprint recognition accuracy. To compensate for the lack of sufficient number of minutiae in poor quality latent prints, we generate a set of virtual minutiae. However, due to a large number of these regularly placed virtual minutiae, texture based template matching has a large computational requirement compared to matching true minutiae templates. To improve both the accuracy and efficiency of the texture template matching, we investigate: i) both original and enhanced fingerprin…
Nanjing University of Posts and Telecommunications（南京邮电大学）
In this paper, we describe work in progress towards a real-time vision-based traffic flow prediction (TFP) system. The proposed method consists of three elemental operators, that are dynamic texture model based motion segmentation, feature extraction and Gaussian process (GP) regression. The objective of motion segmentation is to recognize the target regions covering the moving vehicles in the sequence of visual processes. The feature extraction operator aims to extract useful features from the target regions. The extracted features are then mapped to the number of vehicles through the operato…
An essential aspect of texture analysis is the extraction of features that describe the distribution of values in local, spatial regions. We present a localized histogram layer for artificial neural networks. Instead of computing global histograms as done previously, the proposed histogram layer directly computes the local, spatial distribution of features for texture analysis and parameters for the layer are estimated during backpropagation. We compare our method with state-of-the-art texture encoding methods such as the Deep Encoding Network Pooling, Deep Texture Encoding Network, Fisher Vec…
MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
School of Computer Sciences, Shaanxi Normal University（陕西师范大学计算机科学学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）
AlignVTOFF: Texture-Spatial Feature Alignment for High-Fidelity Virtual Try-Off
Sino-European School of Technology, Shanghai University（上海大学 sino-欧洲技术学院）；National Demonstration Center for Experimental Engineering Training Education, Shanghai University（上海大学国家级实验工程培训教育示范中心）
University of Electronic Science and Technology of China（电子科技大学）；Yibin University（宜宾学院）
In this paper, we proposed an effective face feature extraction method by Learning Gabor Log-Euclidean Gaussian with Whitening Principal Component Analysis (WPCA), called LGLG-WPCA. The proposed method learns face features from the embedded multivariate Gaussian in Gabor wavelet domain; it has the robust performance to adverse conditions such as varying poses, skin aging and uneven illumination. Because the space of Gaussian is a Riemannian manifold and it is difficult to incorporate learning mechanism in the model. To address this issue, we use L2EMG to map the multidimensional Gaussian model…
Velammal College of Engg and Tech（维拉马尔工程技术学院）；Thiagarajar College of Engg（蒂亚加拉贾工程技术学院）
The research work presented in this paper is to achieve the tissue classification and automatically diagnosis the abnormal tumor region present in Computed Tomography (CT) images using the wavelet based statistical texture analysis method. Comparative studies of texture analysis method are performed for the proposed wavelet based texture analysis method and Spatial Gray Level Dependence Method (SGLDM). Our proposed system consists of four phases i) Discrete Wavelet Decomposition (ii) Feature extraction (iii) Feature selection (iv) Analysis of extracted texture features by classifier. A wavelet…
Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-level texture features are directly skip-connected into the deeper layers. Nevertheless, texture features are not only about local structure, but also include global statistical knowledge of the input image. In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation. For the first time, STLNet analyzes the distribu…
Shape from texture refers to the extraction of 3D information from 2D images with irregular texture. This paper introduces a statistical framework to learn shape from texture where convex texture elements in a 2D image are represented through a point process. In a first step, the 2D image is preprocessed to generate a probability map corresponding to an estimate of the unnormalized intensity of the latent point process underlying the texture elements. The latent point process is subsequently inferred from the probability map in a non-parametric, model free manner. Finally, the 3D information i…
Texture analysis and classification remain as one of the biggest challenges for the field of computer vision and pattern recognition. On this matter, Gabor wavelets has proven to be a useful technique to characterize distinctive texture patterns. However, most of the approaches used to extract descriptors of the Gabor magnitude space usually fail in representing adequately the richness of detail present into a unique feature vector. In this paper, we propose a new method to enhance the Gabor wavelets process extracting a fractal signature of the magnitude spaces. Each signature is reduced usin…
Al-Hussein Bin Talal University（侯赛因·本·塔拉勒大学）；University of Mysore（迈索尔大学）
In this paper, we have developed Biometric recognition system adopting hand based modality Handvein, which has the unique pattern for each individual and it is impossible to counterfeit and fabricate as it is an internal feature. We have opted in choosing feature extraction algorithms such as LBP-visual descriptor ,LPQ-blur insensitive texture operator, Log-Gabor-Texture descriptor. We have chosen well known classifiers such as KNN and SVM for classification. We have experimented and tabulated results of single algorithm recognition rate for Handvein under different distance measures and kerne…
This paper is practically interested in the unchangeable feature of Arabic handwritten character. It presents results of comparative study achieved on certain features extraction techniques of handwritten character, based on Hough transform, Fourier transform, Wavelet transform and Gabor Filter. Obtained results show that Hough Transform and Gabor filter are insensible to the rotation and translation, Fourier Transform is sensible to the rotation but insensible to the translation, in contrast to Hough Transform and Gabor filter, Wavelets Transform is sensitive to the rotation as well as to the…
MCNet: A crowd denstity estimation network based on integrating multiscale attention module
College of Mechanical and Electronic Engineering, Dalian Minzu University（大连民族大学机电工程学院）；School of Computer Science and Engineering, Dalian Minzu University（大连民族大学计算机科学与工程学院）；Dalian University of Technology（大连理工大学）；Postdoctoral workstation of Dalian Yongjia Electronic Technology Co., Ltd（大连永佳电子科技有限公司博士后工作站）
Faculty of computer engineering, Najafabad Branch, Islamic azad university（伊斯兰阿扎德大学纳贾法巴德分校计算机工程学院）；Big data research center, Najafabad Branch, Islamic azad university（伊斯兰阿扎德大学纳贾法巴德分校大数据研究中心）
With the development of Information technology and communication, a large part of the databases is dedicated to images and videos. Thus retrieving images related to a query image from a large database has become an important area of research in computer vision. Until now, there are various methods of image retrieval that try to define image contents by texture, color or shape properties. In this paper, a method is presented for image retrieval based on a combination of local texture information derived from two different texture descriptors. First, the color channels of the input image are sep…
Nanjing University of Science and Technology（南京理工大学）；Tencent AI Lab（腾讯人工智能实验室）
We present a large-scale facial UV-texture dataset that contains over 50,000 high-quality texture UV-maps with even illuminations, neutral expressions, and cleaned facial regions, which are desired characteristics for rendering realistic 3D face models under different lighting conditions. The dataset is derived from a large-scale face image dataset namely FFHQ, with the help of our fully automatic and robust UV-texture production pipeline. Our pipeline utilizes the recent advances in StyleGAN-based facial image editing approaches to generate multi-view normalized face images from single-image …
University of Chile（智利大学）；Snap Research（Snap 研究院）；Impresee Inc.（Impresee 公司）
Visual attributes play an essential role in real applications based on image retrieval. For instance, the extraction of attributes from images allows an eCommerce search engine to produce retrieval results with higher precision. The traditional manner to build an attribute extractor is by training a convnet-based classifier with a fixed number of classes. However, this approach does not scale for real applications where the number of attributes changes frequently. Therefore in this work, we propose an approach for extracting visual attributes from images, leveraging the learned capability of t…
This paper is a survey work for a bigger project for designing a Visual SLAM robot to generate 3D dense map of an unknown unstructured environment. A lot of factors have to be considered while designing a SLAM robot. Sensing method of the SLAM robot should be determined by considering the kind of environment to be modeled. Similarly the type of environment determines the suitable feature extraction method. This paper goes through the sensing methods used in some recently published papers. The main objective of this survey is to conduct a comparative study among the current sensing methods and …
King Abdullah II School for Information Technology, University of Jordan（约旦大学阿卜杜拉二世国王信息技术学院）
Meningioma brain tumour discrimination is challenging as many histological patterns are mixed between the different subtypes. In clinical practice, dominant patterns are investigated for signs of specific meningioma pathology; however the simple observation could result in inter- and intra-observer variation due to the complexity of the histopathological patterns. Also employing a computerised feature extraction approach applied at a single resolution scale might not suffice in accurately delineating the mixture of histopathological patterns. In this work we propose a novel multiresolution fea…
University of Waterloo（滑铁卢大学）；University of Toronto（多伦多大学）；Vector Institute（矢量研究院）
Recent advances in digital pathology have led to the need for Histopathology Image Retrieval (HIR) systems that search through databases of biopsy images to find similar cases to a given query image. These HIR systems allow pathologists to effortlessly and efficiently access thousands of previously diagnosed cases in order to exploit the knowledge in the corresponding pathology reports. Since HIR systems may have to deal with millions of gigapixel images, the extraction of compact and expressive image features must be available to allow for efficient and accurate retrieval. In this paper, we p…
Within the domain of texture classification, a lot of effort has been spent on local descriptors, leading to many powerful algorithms. However, preprocessing techniques have received much less attention despite their important potential for improving the overall classification performance. We address this question by proposing a novel, simple, yet very powerful biologically-inspired filtering (BF) which simulates the performance of human retina. In the proposed approach, given a texture image, after applying a DoG filter to detect the "edges", we first split the filtered image into two "maps" …
Robert Bosch GmbH（罗伯特·博世公司）；Norwegian Open AI Lab（挪威开放人工智能实验室）；NTNU（挪威科技大学）
Ground texture based vehicle localization using feature-based methods is a promising approach to achieve infrastructure-free high-accuracy localization. In this paper, we provide the first extensive evaluation of available feature extraction methods for this task, using separately taken image pairs as well as synthetic transformations. We identify AKAZE, SURF and CenSurE as best performing keypoint detectors, and find pairings of CenSurE with the ORB, BRIEF and LATCH feature descriptors to achieve greatest success rates for incremental localization, while SIFT stands out when considering sever…
