Vision Researchers Research Articles

Estimating the perceived dimension of psychophysical stimuli using triplet accuracy and hypothesis testing.

Vision researchers are interested in mapping complex physical stimuli to perceptual dimensions. Such a mapping can be constructed using multidimensional psychophysical scaling or ordinal embedding methods. Both methods infer coordinates that agree as much as possible with the observer's judgments so that perceived similarity corresponds with distance in the inferred space. However, a fundamental problem of all methods that construct scalings in multiple dimensions is that the inferred representation can only reflect perception if the scale has the correct dimension. Here we propose a statistical procedure to overcome this limitation. The critical elements of our procedure are i) measuring the scale's quality by the number of correctly predicted triplets and ii) performing a statistical test to assess if adding another dimension to the scale improves triplet accuracy significantly. We validate our procedure through extensive simulations. In addition, we study the properties and limitations of our procedure using "real" data from various behavioral datasets from psychophysical experiments. We conclude that our procedure can reliably identify (a lower bound on) the number of perceptual dimensions for a given dataset.

Research on saliency detection method based on depth and width neural network

Image saliency detection is to segment the most important areas in the image. Solving the problem of image saliency detection usually involves knowledge in computer vision, neuroscience, cognitive psychology and other fields. In recent years, as deep learning has made great achievements in the field of computer vision, the application of deep learning has also played a good role in image saliency detection. Therefore, algorithms based on deep convolutional neural networks have become solutions to image saliency The most effective method of detection. For researchers, improving the computational efficiency of neural network-based saliency detection algorithms generally starts from two perspectives. One is to tailor the network structure and combine traditional feature extraction methods for processing. The other is to use a lighter network to solve the saliency detection problem. Based on these two points of thinking, this paper proposes two efficient and accurate neural network-based saliency detection algorithms. In recent years, with the rapid development of multimedia and Internet technologies, a huge amount of picture information is generated on blogs, social networking or shopping platforms every day. Such a lot of information not only enriches people's lives, but also provides efficient and accurate network management platforms. The management of these image information brings difficulties. Therefore, how to understand and process these image information more intelligently and efficiently has become a hot topic for many image processing and computer vision researchers. Among them, the saliency detection technology plays a key role in solving the problem of intelligent understanding and processing of images. To put it simply, saliency detection is a technology to automatically calculate or detect the most important areas in an image, and its processing results provide a basis for understanding and processing the image content. Saliency detection is a basic problem in computer vision, neuroscience and visual perception. The algorithm detects and extracts the most interesting or significant areas in the image.

Multimodal brain tumor detection and classification using deep saliency map and improved dragonfly optimization algorithm

AbstractIn the last decade, there has been a significant increase in medical cases involving brain tumors. Brain tumor is the tenth most common type of tumor, affecting millions of people. However, if it is detected early, the cure rate can increase. Computer vision researchers are working to develop sophisticated techniques for detecting and classifying brain tumors. MRI scans are primarily used for tumor analysis. We proposed an automated system for brain tumor detection and classification using a saliency map and deep learning feature optimization in this paper. The proposed framework was implemented in stages. In the initial phase of the proposed framework, a fusion‐based contrast enhancement technique is proposed. In the following phase, a tumor segmentation technique based on saliency maps is proposed, which is then mapped on original images based on active contour. Following that, a pre‐trained CNN model named EfficientNetB0 is fine‐tuned and trained in two ways: on enhanced images and on tumor localization images. Deep transfer learning is used to train both models, and features are extracted from the average pooling layer. The deep learning features are then fused using an improved fusion approach known as Entropy Serial Fusion. The best features are chosen in the final step using an improved dragonfly optimization algorithm. Finally, the best features are classified using an extreme learning machine (ELM). The experimental process is conducted on three publically available datasets and achieved an improved accuracy of 95.14, 94.89, and 95.94%, respectively. The comparison with several neural nets shows the improvement of proposed framework.

Explainable Deep Learning approach for Shoulder Abnormality Detection in X-Rays Dataset

Computer vision researchers and decision-makers have struggled to understand how deep neural networks (DNNs) accomplish image classification tasks and interpret their results. Due to a lack of understanding of their internal functioning, these models are commonly referred to as "black boxes." As a part of the development process, the DNNs can be easily explained. In this research work, we introduce an explainable technique for shoulder abnormality detection. The motivation behind this study is to enhance patients' and medical professionals' trust in DNNs technology. DNNs are implemented frequently in the medical domain. The suggested abnormality detector, which is based on IGrad-CAM++, is capable of detecting Shoulder X-rays abnormality. Grad-CAM is a common approach that combines the activation maps received from the model to create such a visualization. The average gradient-based terms used in this technique, on the other hand, understate the contribution of the model's identified representations to its predictions. In order to address this issue, we offer a technique that uses Grad-CAM++ to compute the route integral of the gradient-based terms. By assessing different techniques, it is discovered that the recommended procedure can perform very effectively and efficiently in X-ray images provides more visual explanation than existing techniques.

Real-Time Face Recognition Civil Servant Presence System Using DNN Algorithm

Facial recognition has become a growing topic among Computer Vision researchers because it can solve real-life problems, including during the COVID-19 pandemic. The pandemic is why the Indonesian government has imposed social restrictions and physical contact in public places. Before the pandemic, most touch-based attendance systems used fingerprints or Radio Frequency Identification (RFID) cards. The solution proposed in this study is to identify real-time facial recognition of the Civil Service presence system using a Deep Neural Network. The goal is to minimize physical contact. The research stages include data collection, augmentation and preprocessing, CNN modeling and training, model evaluation, converting to OpenCV DNN, implementation of transfer learning, and identification of test data. This research contributes to testing variations in distance and position so it can recognize a person's face even when wearing a mask and glasses. This DNN model produces a validation accuracy value of 99.48% and a validation loss of 0.0273 with a data training process of 10 times. Tests for variations in distance, position, use of masks, and glasses on MTCNN detection provide an average accuracy for each trial of 100%, 96%, and 100%, respectively. Therefore, the average accuracy of the Haar Cascades detection test is 100%, 85%, and 100%.

The Core of Smart Cities: Knowledge Representation and Descriptive Framework Construction in Knowledge-Based Visual Question Answering

Visual question answering (VQA), which is an important presentation form of AI-complete task and visual Turing tests, coupled with its potential application value, attracted widespread attention from both researchers in computer vision and natural language processing. However, there are no relevant research regarding the expression and participation methods of knowledge in VQA. Considering the importance of knowledge for answering questions correctly, this paper analyzes and researches the stratification, expression and participation process of knowledge in VQA and proposes a knowledge description framework (KDF) to guide the research of knowledge-based VQA (Kb-VQA). The KDF consists of a basic theory, implementation methods and specific applications. This paper focuses on describing mathematical models at basic theoretical levels, as well as the knowledge hierarchy theories and key implementation behaviors established on this basis. In our experiment, using the statistics of VQA’s accuracy in the relevant literature, we propose a good corroboration of the research results from knowledge stratification, participation methods and expression forms in this paper.

Feminist Social Vision: Seeing Through the Lens of Marginalized Perceivers

Social vision research, which examines, in part, how humans visually perceive social stimuli, is well-positioned to improve understandings of social inequality. However, social vision research has rarely prioritized the perspectives of marginalized group members. We offer a theoretical argument for diversifying understandings of social perceptual processes by centering marginalized perspectives. We examine (a) how social vision researchers frame their research questions and who these framings prioritize and (b) how perceptual processes (person perception; people perception; perception of social objects) are linked to group membership and thus comprehensively understanding these processes necessitates attention to marginalized perceivers. We discuss how social vision research translates into theoretical advances and to action for reducing negative intergroup consequences (e.g., prejudice). The purpose of this article is to delineate how prioritizing marginalized perspectives in social vision research could develop novel questions, bridge theoretical gaps, and elevate social vision’s translational impact to improve outcomes for marginalized groups. Public Social vision research is a subfield of psychology and vision science which examines how people visually perceive social stimuli and what the downstream consequences of these perceptions are. Social vision work includes, for example, examination of how White people visually perceive racial minorities and how these perceptions lead to social categorizations of racial minorities as outgroups, and therefore contribute to behaviors such as stereotyping and prejudice. Social vision research has rarely prioritized the perspectives of marginalized group members. It therefore cannot fully explain the contributions of perception to intergroup relations, which are necessarily bidirectional. We offer a theoretical argument for diversifying understandings of social perceptual processes by centering marginalized perspectives to understand how people with marginalized identities see their social worlds. We believe that prioritizing these marginalized perspectives has the potential to contribute to the development of a psychological science with heightened capacity to improve the well-being of people with marginalized identities.

Online Multiplayer Tracking by Extracting Temporal Contexts with Transformer

Sports competition is one of the most popular programs for many audiences. Tracking the players in sports game videos from broadcasts is a nontrivial challenge for computer vision researchers. In sports videos, the direction of an athlete’s movement changes quickly and unpredictably. Mutual occlusion between athletes is also more frequent in team competitions. However, the rich temporal contexts among the adjacent frames have been excluded from consideration. To address this dilemma, we propose an online transformer-based learnable framework in an end-to-end fashion. We use a transformer architecture to extract the temporal contexts between the successive frames and add them to the network training, which is robust to occlusion and complex direction changes in multiplayer tracking. We demonstrate the effectiveness of our method on three sports video datasets by comparing them with recently advanced multiplayer trackers.

Detection and Classification of Human-Carrying Baggage Using DenseNet-161 and Fit One Cycle

In recent decades, the crime rate has significantly increased. As a result, the automatic video monitoring system has become increasingly important for researchers in computer vision. A person’s baggage classification is essential in knowing who has abandoned baggage. This paper proposes a model for classifying humans carrying baggage. Two approaches are used for comparison using a deep learning technique. The first approach is based on categorizing human-containing image regions as either with or without baggage. The second approach classifies human-containing image regions based on the human position direction attribute. The proposed model is based on the pretrained DenseNet-161 architecture. It uses a "fit-one-cycle policy" strategy to reduce the training time and achieve better accuracy. The Fastai framework is used for implementation due to its super computational ability, simple workflow, and unique data cleansing functionalities. Our proposed model was experimentally validated, and the results show that the process is sufficiently precise, faster, and outperforms the existing methods. We achieved an accuracy of between 96% and 98.75% for the binary classification and 96.67% and 98.33% for the multi-class classification. For multi-class classification, the datasets, such as PETA, INRIA, ILIDS, and MSMT17, are re-annotated with one’s direction information about one’s stance to test the suggested approach’s efficacy.

Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution

The past few years have seen an accelerating integration of deep learning (DL) techniques into various remote sensing (RS) applications, highlighting their power to adapt and achieving unprecedented advancements. In the present review, we provide an exhaustive exploration of the DL approaches proposed specifically for the spatial downscaling of RS imagery. A key contribution of our work is the presentation of the major architectural components and models, metrics, and data sets available for this task as well as the construction of a compact taxonomy for navigating through the various methods. Furthermore, we analyze the limitations of the current modeling approaches and provide a brief discussion on promising directions for image enhancement, following the paradigm of general computer vision (CV) practitioners and researchers as a source of inspiration and constructive insight.

Performance Evaluation of Recurrent Neural Networks Applied to Indoor Camera Localization

Researchers in robotics and computer vision are experimenting with the image-based localization of indoor cameras. Implementation of indoor camera localization problems using a Convolutional neural network (CNN) or Recurrent neural network (RNN) is more challenging from a large image dataset because of the internal structure of CNN or RNN. We can choose a preferable CNN or RNN variant based on the problem type and size of the dataset. CNN is the most flexible method for implementing indoor localization problems. Despite CNN's suitability for hyper-parameter selection, it requires a lot of training images to achieve high accuracy. In addition, overfitting leads to a decrease in accuracy. Introduce RNN, which accurately keeps input images in internal memory to solve these problems. Longshort-term memory (LSTM), Bi-directional LSTM (BiLSTM), and Gated recurrent unit (GRU) are three variants of RNN. We may choose the most appropriate RNN variation based on the problem type and dataset. In this study, we can recommend which variant is effective for training more speedily and which variant produces more accurate results. Vanishing gradient issues also affect RNNs, making it difficult to learn more data. Overcome the gradient vanishing problem by utilizing LSTM. The BiLSTM is an advanced version of the LSTM and is capable of higher performance than the LSTM. A more advanced RNN variant is GRU which is computationally more efficient than an LSTM. In this study, we explore a variety of recurring units for localizing indoor cameras. Our focus is on more powerful recurrent units like LSTM, BiLSTM, and GRU. Using the Microsoft 7-Scenes and InteriorNet datasets, we evaluate the performance of LSTM, BiLSTM, and GRU. Our experiment has shown that the BiLSTM is more efficient in accuracy than the LSTM and GRU. We also observed that the GRU is faster than LSTM and BiLSTM

DEFUSE: Deep Fused End-to-End Video Text Detection and Recognition

Detecting and recognizing text in natural scene videos and images has brought more attention to computer vision researchers due to applications like robotic navigation and traffic sign detection. In addition, Optical Character Recognition (OCR) technology is applied to detect and recognize text on the license plate. It will be used in various commercial applications such as finding stolen cars, calculating parking fees, invoicing tolls, or controlling access to safety zones and aids in detecting fraud and secure data transactions in the banking industry. Much effort is required when scene text videos are in low contrast and motion blur with arbitrary orientations. Presently, text detection and recognition approaches are limited to static images like horizontal or approximately horizontal text. Detecting and recognizing text in videos with data dynamicity is more challenging because of the presence of multiple blurs caused by defocusing, motion, illumination changes, arbitrarily shaped, and occlusion. Thus, we proposed a combined DeepEAST (Deep Efficient and Accurate Scene Text Detector) and Keras OCR model to overcome these challenges in the proffered DEFUSE (Deep Fused) work. This two-combined technique detects the text regions and then deciphers the result into a machine-readable format. The proposed method has experimented with three different video datasets such as ICDAR 2015, Road Text 1K, and own video Datasets. Our results proved to be more effective with precision, recall, and F1-Score.

A SURVY of video datasets for anomaly detection and human activity recognition

The computer vision researchers concentrated on the automation of the surveillance system. Many datasets suited for diverse applications have been proposed by research in this subject. in a number of different domains of application Human action recognition may be used effectively, which has the potential to improve many facets of daily life.These contain, among other things, preventing violent act and detecting crimes such as murder, stealing, and property damage, as well as predicting pedestrian activity in traffic. And this study addresses the properties of public datasets used for Human Action Recognition. Researchers develop these distinct anomaly datasets as a result of the availability of security cameras installed in various areas. For researchers to comprehend and develop in this field, It is required to review anomaly detection video datasets. Therefor This study presents a survey for video surveillance activity recognition.

Personal Re-identification Using Incremental Dynamic Time Warping Algorithm and Body Measuremen

Identification of unique individuals is being extensively used in security and surveillance. Gait recognition has caught the attention of computer vision researchers. This interest has been stimulated by the development of systems to automatically identify individuals. This paper presents a gait gesture recognition algorithm, using Incremental Dynamic Time Warping (IDTW) with a body measurement technique that identifies personal gait patterns recorded on video via Microsoft’s Kinect® 3D depth-sensing camera. We used the height of a person to further clarify the recognition and accurate identification of the individual. The initial results demonstrated 81.25% accuracy with our gait and height recognition algorithm. This recognition technique is ideal for high-level security requirements.

Flukebook: an open-source AI platform for cetacean photo identification

Determining which species are at greatest risk, where they are most vulnerable, and what are the trajectories of their communities and populations is critical for conservation and management. Globally distributed, wide-ranging whales and dolphins present a particular challenge in data collection because no single research team can record data over biologically meaningful areas. Flukebook.org is an open-source web platform that addresses these gaps by providing researchers with the latest computational tools. It integrates photo-identification algorithms with data management, sharing, and privacy infrastructure for whale and dolphin research, enabling the global collaborative study of these global species. With seven automatic identification algorithms trained for 15 different species, resulting in 37 species-specific identification pipelines, Flukebook is an extensible foundation that continually incorporates emerging AI techniques and applies them to cetacean photo identification through continued collaboration between computer vision researchers, software engineers, and biologists. With over 2.0 million photos of over 52,000 identified individual animals submitted by over 250 researchers, the platform enables a comprehensive understanding of cetacean populations, fostering international and cross-institutional collaboration while respecting data ownership and privacy. We outline the technology stack and architecture of Flukebook, its performance on real-world cetacean imagery, and its development as an example of scalable, extensible, and reusable open-source conservation software. Flukebook is a step change in our ability to conduct large-scale research on cetaceans across biologically meaningful geographic ranges, to rapidly iterate population assessments and abundance trajectories, and engage the public in actions to protect them.

Analysis of the Reliability and Repeatability of Distance Visual Acuity Measurement with EyeSpy 20/20.

BackgroundVisual acuity is a critical component of visual function assessment for all ages. Standardized vision testing protocols may help prevent testing inconsistencies resulting from variations in test administration and interpretation of different examiners. However, most vision assessments outside of research settings, including in doctor’s offices, rarely employ standardized protocols. Validated protocols such as the Early Treatment for Diabetic Retinopathy Study (ETDRS) are frequently employed by vision researchers to ensure accurate and repeatable visual acuity measurements.MethodsThis study evaluates a desktop-based standardized vision testing algorithm (EyeSpy 20/20) specifically designed for use on mobile electronic platforms. Subjects were tested on a desktop version of the EyeSpy software for both the accuracy and duration of measurement of visual acuity and compared to a e-ETDRS chart in a randomized sequence. Children were recruited for this study and tested between two different visual acuity measurement systems. Bland–Altman analysis and correlation tests were done.ResultsHundred and ten children were recruited for the study. The EyeSpy 20/20 visual acuity testing algorithm as tested with the desktop version was non-inferior to the gold standard e-ETDRS testing algorithm on a desktop platform, but statistically faster to implement when administered on the same electronic testing platform.ConclusionEyeSpy 20/20 is a promising tool for vision screening and visual acuity evaluation in children.

Benchmarking deep networks for facial emotion recognition in the wild

Emotion recognition from face images is a challenging task that gained interest in recent years for its applications to business intelligence and social robotics. Researchers in computer vision and affective computing focused on optimizing the classification error on benchmark data sets, which do not extensively cover possible variations that face images may undergo in real environments. Following on investigations carried out in the field of object recognition, we evaluated the robustness of existing methods for emotion recognition when their input is subjected to corruptions caused by factors present in real-world scenarios. We constructed two data sets on top of the RAF-DB test set, named RAF-DB-C and RAF-DB-P, that contain images modified with 18 types of corruption and 10 of perturbation. We benchmarked existing networks (VGG, DenseNet, SENet and Xception) trained on the original images of RAF-DB and compared them with ARM, the current state-of-the-art method on the RAF-DB test set. We carried out an extensive study on the effects that modifications to the training data or network architecture have on the classification of corrupted and perturbed data. We observed a drop of recognition performance of ARM, with the classification error raising up to 200% of that achieved on the original RAF-DB test set. We demonstrate that the use of the AutoAugment data augmentation and an anti-aliasing filter within down-sampling layers provide existing networks with increased robustness to out-of-distribution variations, substantially reducing the error on corrupted inputs and outperforming ARM. We provide insights about the resilience of existing emotion recognition methods and an estimation of their performance in real scenarios. The processing time required by the modifications we investigated (35 ms in the worst case) supports their suitability for application in real-world scenarios. The RAF-DB-C and RAF-DB-P test sets, trained models and evaluation framework are available at https://github.com/MiviaLab/emotion-robustness.

Optical tracking in team sports

Abstract Sports analysis has gained paramount importance for coaches, scouts, and fans. Recently, computer vision researchers have taken on the challenge of collecting the necessary data by proposing several methods of automatic player and ball tracking. Building on the gathered tracking data, data miners are able to perform quantitative analysis on the performance of players and teams. With this survey, our goal is to provide a basic understanding for quantitative data analysts about the process of creating the input data and the characteristics thereof. Thus, we summarize the recent methods of optical tracking by providing a comprehensive taxonomy of conventional and deep learning methods, separately. Moreover, we discuss the preprocessing steps of tracking, the most common challenges in this domain, and the application of tracking data to sports teams. Finally, we compare the methods by their cost and limitations, and conclude the work by highlighting potential future research directions.

Intelligent Robotics and Industrial Applications using Computer Vision 2022 Conference Overview and Papers Program

This conference brings together real-world practitioners and researchers in intelligent robots and computer vision to share recent applications and developments. Topics of interest include the integration of imaging sensors supporting hardware, computers, and algorithms for intelligent robots, manufacturing inspection, characterization, and/or control. The decreased cost of computational power and vision sensors has motivated the rapid proliferation of machine vision technology in a variety of industries, including aluminum, automotive, forest products, textiles, glass, steel, metal casting, aircraft, chemicals, food, fishing, agriculture, archaeological products, medical products, artistic products, etc. Other industries, such as semiconductor and electronics manufacturing, have been employing machine vision technology for several decades. Machine vision supporting handling robots is another main topic. With respect to intelligent robotics another approach is sensor fusion – combining multi-modal sensors in audio, location, image and video data for signal processing, machine learning and computer vision, and additionally other 3D capturing devices. There is a need for accurate, fast, and robust detection of objects and their position in space. Their surface, background, and illumination are uncontrolled, and in most cases the objects of interest are within a bulk of many others. For both new and existing industrial users of machine vision, there are numerous innovative methods to improve productivity, quality, and compliance with product standards. There are several broad problem areas that have received significant attention in recent years. For example, some industries are collecting enormous amounts of image data from product monitoring systems. New and efficient methods are required to extract insight and to perform process diagnostics based on this historical record. Regarding the physical scale of the measurements, microscopy techniques are nearing resolution limits in fields such as semiconductors, biology, and other nano-scale technologies. Techniques such as resolution enhancement, model-based methods, and statistical imaging may provide the means to extend these systems beyond current capabilities. Furthermore, obtaining real-time and robust measurements in-line or at-line in harsh industrial environments is a challenge for machine vision researchers, especially when the manufacturer cannot make significant changes to their facility or process.

DEEP LEARNING APPROACH FOR URBAN MAPPING

Abstract. Researchers in computer vision and machine learning are becoming increasingly interested in image semantic segmentation. Many methods based on convolutional neural networks (CNNs) have been proposed and have made considerable progress in the building extraction mission. This other methods can result in suboptimal segmentation outcomes. Recently, to extract buildings with a great precision, we propose a model which can recognize all the buildings and present them in mask with white and the other classes in black. This developed network, which is based on U-Net, will boost the model's sensitivity. This paper provides a deep learning approach for building detection on satellite imagery applied in Casablanca city, Firstly, to begin we describe the terminology of this field. Next, the main datasets exposed in this project which’s 1000 satellite imagery. Then, we train the model UNET for 25 epochs on the training and validation datasets and testing the pretrained weight model with some unseen satellite images. Finally, the experimental results show that the proposed model offers good performance obtained as a binary mask that extract all the buildings in the region of Casablanca with a higher accuracy and entirety to achieve an average F1 score on test data of 0.91.