arXiv subjects

Computer vision

Explore arXiv computer-vision papers and cs.CV metadata. Search within the index for image segmentation, object detection and visual representation learning.

Follow this topic with RSS

At least 595 records · Page 33Linked to original sources

arXiv2021

Automatic Visual Inspection of Rare Defects: A Framework based on GP-WGAN and Enhanced Faster R-CNN

A current trend in industries such as semiconductors and foundry is to shift their visual inspection processes to Automatic Visual Inspection (AVI) systems, to reduce their costs, mistakes, and dependency on human experts. This paper proposes a two-staged fault diagnosis framework for AVI systems. In the first stage, a generation model is designed to synthesize new samples based on real samples. The proposed augmentation algorithm extracts objects from the real samples and blends them randomly, to generate new samples and enhance the performance of the image processor. In the second stage, an improved deep learning architecture based on Faster R-CNN, Feature Pyramid Network (FPN), and a Residual Network is proposed to perform object detection on the enhanced dataset. The performance of the algorithm is validated and evaluated on two multi-class datasets. The experimental results performed over a range of imbalance severities demonstrate the superiority of the proposed framework compared to other solutions.

cs.CV↗

arXiv2013

Unsupervised ensemble of experts (EoE) framework for automatic binarization of document images

In recent years, a large number of binarization methods have been developed, with varying performance generalization and strength against different benchmarks. In this work, to leverage on these methods, an ensemble of experts (EoE) framework is introduced, to efficiently combine the outputs of various methods. The proposed framework offers a new selection process of the binarization methods, which are actually the experts in the ensemble, by introducing three concepts: confidentness, endorsement and schools of experts. The framework, which is highly objective, is built based on two general principles: (i) consolidation of saturated opinions and (ii) identification of schools of experts. After building the endorsement graph of the ensemble for an input document image based on the confidentness of the experts, the saturated opinions are consolidated, and then the schools of experts are identified by thresholding the consolidated endorsement graph. A variation of the framework, in which no selection is made, is also introduced that combines the outputs of all experts using endorsement-dependent weights. The EoE framework is evaluated on the set of participating methods in the H-DIBCO'12 contest and also on an ensemble generated from various instances of grid-based Sauvola method with promising performance.

cs.CV↗

arXiv2025

mmWave Radar-Based Non-Line-of-Sight Pedestrian Localization at T-Junctions Utilizing Road Layout Extraction via Camera

Pedestrians Localization in Non-Line-of-Sight (NLoS) regions within urban environments poses a significant challenge for autonomous driving systems. While mmWave radar has demonstrated potential for detecting objects in such scenarios, the 2D radar point cloud (PCD) data is susceptible to distortions caused by multipath reflections, making accurate spatial inference difficult. Additionally, although camera images provide high-resolution visual information, they lack depth perception and cannot directly observe objects in NLoS regions. In this paper, we propose a novel framework that interprets radar PCD through road layout inferred from camera for localization of NLoS pedestrians. The proposed method leverages visual information from the camera to interpret 2D radar PCD, enabling spatial scene reconstruction. The effectiveness of the proposed approach is validated through experiments conducted using a radar-camera system mounted on a real vehicle. The localization performance is evaluated using a dataset collected in outdoor NLoS driving environments, demonstrating the practical applicability of the method.

cs.CV↗

arXiv2011

A prototype system for handwritten sub-word recognition: Toward Arabic-manuscript transliteration

A prototype system for the transliteration of diacritics-less Arabic manuscripts at the sub-word or part of Arabic word (PAW) level is developed. The system is able to read sub-words of the input manuscript using a set of skeleton-based features. A variation of the system is also developed which reads archigraphemic Arabic manuscripts, which are dot-less, into archigraphemes transliteration. In order to reduce the complexity of the original highly multiclass problem of sub-word recognition, it is redefined into a set of binary descriptor classifiers. The outputs of trained binary classifiers are combined to generate the sequence of sub-word letters. SVMs are used to learn the binary classifiers. Two specific Arabic databases have been developed to train and test the system. One of them is a database of the Naskh style. The initial results are promising. The systems could be trained on other scripts found in Arabic manuscripts.

cs.CV↗

arXiv2021

Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator

Existing remote sensing change detection methods are heavily affected by seasonal variation. Since vegetation colors are different between winter and summer, such variations are inclined to be falsely detected as changes. In this letter, we proposed an image translation method to solve the problem. A style-based recalibration module is introduced to capture seasonal features effectively. Then, a new style discriminator is designed to improve the translation performance. The discriminator can not only produce a decision for the fake or real sample, but also return a style vector according to the channel-wise correlations. Extensive experiments are conducted on season-varying dataset. The experimental results show that the proposed method can effectively perform image translation, thereby consistently improving the season-varying image change detection performance. Our codes and data are available at https://github.com/summitgao/RSIT_SRM_ISD.

cs.CV↗

arXiv2018

Fractional Wavelet Scattering Network and Applications

Objective: The present study introduces a fractional wavelet scattering network (FrScatNet), which is a generalized translation invariant version of the classical wavelet scattering network (ScatNet). Methods: In our approach, the FrScatNet is constructed based on the fractional wavelet transform (FRWT). The fractional scattering coefficients are iteratively computed using FRWTs and modulus operators. The feature vectors constructed by fractional scattering coefficients are usually used for signal classification. In this work, an application example of FrScatNet is provided in order to assess its performance on pathological images. Firstly, the FrScatNet extracts feature vectors from patches of the original histological images under different orders. Then we classify those patches into target (benign or malignant) and background groups. And the FrScatNet property is analyzed by comparing error rates computed from different fractional orders respectively. Based on the above pathological image classification, a gland segmentation algorithm is proposed by combining the boundary information and the gland location. Results: The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is significantly improved in fractional scattering domain. We also compare the FrScatNet based gland segmentation method with those proposed in the 2015 MICCAI Gland Segmentation Challenge and our method achieves comparable results. Conclusion: The FrScatNet is shown to achieve accurate and robust results. More stable and discriminative fractional scattering coefficients are obtained by the FrScatNet in this work. Significance: The added fractional order parameter is able to analyze the image in the fractional scattering domain.

cs.CV↗

arXiv2025

Experimental investigation of pose informed reinforcement learning for skid-steered visual navigation

Vision-based lane keeping is a topic of significant interest in the robotics and autonomous ground vehicles communities in various on-road and off-road applications. The skid-steered vehicle architecture has served as a useful vehicle platform for human controlled operations. However, systematic modeling, especially of the skid-slip wheel terrain interactions (primarily in off-road settings) has created bottlenecks for automation deployment. End-to-end learning based methods such as imitation learning and deep reinforcement learning, have gained prominence as a viable deployment option to counter the lack of accurate analytical models. However, the systematic formulation and subsequent verification/validation in dynamic operation regimes (particularly for skid-steered vehicles) remains a work in progress. To this end, a novel approach for structured formulation for learning visual navigation is proposed and investigated in this work. Extensive software simulations, hardware evaluations and ablation studies now highlight the significantly improved performance of the proposed approach against contemporary literature.

cs.RO↗

arXiv2018

Multi-Instance Dynamic Ordinal Random Fields for Weakly-supervised Facial Behavior Analysis

We propose a Multi-Instance-Learning (MIL) approach for weakly-supervised learning problems, where a training set is formed by bags (sets of feature vectors or instances) and only labels at bag-level are provided. Specifically, we consider the Multi-Instance Dynamic-Ordinal-Regression (MI-DOR) setting, where the instance labels are naturally represented as ordinal variables and bags are structured as temporal sequences. To this end, we propose Multi-Instance Dynamic Ordinal Random Fields (MI-DORF). In this framework, we treat instance-labels as temporally-dependent latent variables in an Undirected Graphical Model. Different MIL assumptions are modelled via newly introduced high-order potentials relating bag and instance-labels within the energy function of the model. We also extend our framework to address the Partially-Observed MI-DOR problems, where a subset of instance labels are available during training. We show on the tasks of weakly-supervised facial behavior analysis, Facial Action Unit (DISFA dataset) and Pain (UNBC dataset) Intensity estimation, that the proposed framework outperforms alternative learning approaches. Furthermore, we show that MIDORF can be employed to reduce the data annotation efforts in this context by large-scale.

cs.CV↗

arXiv2021

Revisiting Shadow Detection: A New Benchmark Dataset for Complex World

Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.

cs.CV↗

arXiv2017

A Functional Regression approach to Facial Landmark Tracking

Linear regression is a fundamental building block in many face detection and tracking algorithms, typically used to predict shape displacements from image features through a linear mapping. This paper presents a Functional Regression solution to the least squares problem, which we coin Continuous Regression, resulting in the first real-time incremental face tracker. Contrary to prior work in Functional Regression, in which B-splines or Fourier series were used, we propose to approximate the input space by its first-order Taylor expansion, yielding a closed-form solution for the continuous domain of displacements. We then extend the continuous least squares problem to correlated variables, and demonstrate the generalisation of our approach. We incorporate Continuous Regression into the cascaded regression framework, and show its computational benefits for both training and testing. We then present a fast approach for incremental learning within Cascaded Continuous Regression, coined iCCR, and show that its complexity allows real-time face tracking, being 20 times faster than the state of the art. To the best of our knowledge, this is the first incremental face tracker that is shown to operate in real-time. We show that iCCR achieves state-of-the-art performance on the 300-VW dataset, the most recent, large-scale benchmark for face tracking.

cs.CV↗

arXiv2018

Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning

The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the computation of the forward pass in a CNN is equivalent to a pursuit algorithm aiming to estimate the nested sparse representation vectors -- or feature maps -- from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, a deeper understanding of the ML-CSC is still lacking: there are no pursuit algorithms that can serve this model exactly, nor are there conditions to guarantee a non-empty model. While one can easily obtain signals that approximately satisfy the ML-CSC constraints, it remains unclear how to simply sample from the model and, more importantly, how one can train the convolutional filters from real data. In this work, we propose a sound pursuit algorithm for the ML-CSC model by adopting a projection approach. We provide new and improved bounds on the stability of the solution of such pursuit and we analyze different practical alternatives to implement this in practice. We show that the training of the filters is essential to allow for non-trivial signals in the model, and we derive an online algorithm to learn the dictionaries from real data, effectively resulting in cascaded sparse convolutional layers. Last, but not least, we demonstrate the applicability of the ML-CSC model for several applications in an unsupervised setting, providing competitive results. Our work represents a bridge between matrix factorization, sparse dictionary learning and sparse auto-encoders, and we analyze these connections in detail.

cs.CV↗

arXiv2025

Quality assessment of 3D human animation: Subjective and objective evaluation

Virtual human animations have a wide range of applications in virtual and augmented reality. While automatic generation methods of animated virtual humans have been developed, assessing their quality remains challenging. Recently, approaches introducing task-oriented evaluation metrics have been proposed, leveraging neural network training. However, quality assessment measures for animated virtual humans that are not generated with parametric body models have yet to be developed. In this context, we introduce a first such quality assessment measure leveraging a novel data-driven framework. First, we generate a dataset of virtual human animations together with their corresponding subjective realism evaluation scores collected with a user study. Second, we use the resulting dataset to learn predicting perceptual evaluation scores. Results indicate that training a linear regressor on our dataset results in a correlation of 90%, which outperforms a state of the art deep learning baseline.

cs.GR↗

arXiv2023

Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives

Action scene understanding in soccer is a challenging task due to the complex and dynamic nature of the game, as well as the interactions between players. This article provides a comprehensive overview of this task divided into action recognition, spotting, and spatio-temporal action localization, with a particular emphasis on the modalities used and multimodal methods. We explore the publicly available data sources and metrics used to evaluate models' performance. The article reviews recent state-of-the-art methods that leverage deep learning techniques and traditional methods. We focus on multimodal methods, which integrate information from multiple sources, such as video and audio data, and also those that represent one source in various ways. The advantages and limitations of methods are discussed, along with their potential for improving the accuracy and robustness of models. Finally, the article highlights some of the open research questions and future directions in the field of soccer action recognition, including the potential for multimodal methods to advance this field. Overall, this survey provides a valuable resource for researchers interested in the field of action scene understanding in soccer.

cs.CV↗

arXiv2025

DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey

Reinforcement learning (RL)-based large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, have attracted widespread attention for their remarkable capabilities in multimodal data understanding. Meanwhile, the rapid expansion of information services has led to a growing demand for AI-enabled wireless networks. The open-source DeepSeek models are famous for their innovative designs, such as large-scale pure RL and cost-efficient training, which make them well-suited for practical deployment in wireless networks. By integrating DeepSeek-style LLMs with wireless infrastructures, a synergistic opportunity arises: the DeepSeek-style LLMs enhance network optimization with strong reasoning and decision-making abilities, while wireless infrastructure enables the broad deployment of these models. Motivated by this convergence, this survey presents a comprehensive DeepSeek-inspired exploration of RL-based LLMs in the context of wireless networks. We begin by reviewing key techniques behind network optimization to establish a foundation for understanding DeepSeek-style LLM integration. Next, we examine recent advancements in RL-based LLMs, using DeepSeek models as a representative example. Building on this, we explore the synergy between the two domains, highlighting motivations, challenges, and potential solutions. Finally, we highlight emerging directions for integrating LLMs with wireless networks, such as quantum, on-device, and neural-symbolic LLM models, as well as embodied AI agents. Overall, this survey offers a comprehensive examination of the interplay between DeepSeek-style LLMs and wireless networks, demonstrating how these domains can mutually enhance each other to drive innovation.

cs.LG↗

arXiv2018

Efficient and accurate inversion of multiple scattering with deep learning

Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and regularization is used to enforce prior constraints on the object. In this paper, we propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network that can invert multiple scattered measurements to produce a high-quality image of the refractive index. Our results on both simulated and experimental datasets show that the proposed approach is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.

cs.CV↗

arXiv2013

PCG-Cut: Graph Driven Segmentation of the Prostate Central Gland

Prostate cancer is the most abundant cancer in men, with over 200,000 expected new cases and around 28,000 deaths in 2012 in the US alone. In this study, the segmentation results for the prostate central gland (PCG) in MR scans are presented. The aim of this research study is to apply a graph-based algorithm to automated segmentation (i.e. delineation) of organ limits for the prostate central gland. The ultimate goal is to apply automated segmentation approach to facilitate efficient MR-guided biopsy and radiation treatment planning. The automated segmentation algorithm used is graph-driven based on a spherical template. Therefore, rays are sent through the surface points of a polyhedron to sample the graph's nodes. After graph construction - which only requires the center of the polyhedron defined by the user and located inside the prostate center gland - the minimal cost closed set on the graph is computed via a polynomial time s-t-cut, which results in the segmentation of the prostate center gland's boundaries and volume. The algorithm has been realized as a C++ modul within the medical research platform MeVisLab and the ground truth of the central gland boundaries were manually extracted by clinical experts (interventional radiologists) with several years of experience in prostate treatment. For evaluation the automated segmentations of the proposed scheme have been compared with the manual segmentations, yielding an average Dice Similarity Coefficient (DSC) of 78.94 +/- 10.85%.

cs.CV↗

arXiv2025

GEA: Generation-Enhanced Alignment for Text-to-Image Person Retrieval

Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect the content of the image, leading to poor cross-modal alignment and overfitting to limited datasets. Moreover, the inherent modality gap between text and image further amplifies these issues, making accurate cross-modal retrieval even more challenging. To address these limitations, we propose the Generation-Enhanced Alignment (GEA) from a generative perspective. GEA contains two parallel modules: (1) Text-Guided Token Enhancement (TGTE), which introduces diffusion-generated images as intermediate semantic representations to bridge the gap between text and visual patterns. These generated images enrich the semantic representation of text and facilitate cross-modal alignment. (2) Generative Intermediate Fusion (GIF), which combines cross-attention between generated images, original images, and text features to generate a unified representation optimized by triplet alignment loss. We conduct extensive experiments on three public TIPR datasets, CUHK-PEDES, RSTPReid, and ICFG-PEDES, to evaluate the performance of GEA. The results justify the effectiveness of our method. More implementation details and extended results are available at https://github.com/sugelamyd123/Sup-for-GEA.

cs.CV↗

arXiv2013

Single image super resolution in spatial and wavelet domain

Recently single image super resolution is very important research area to generate high resolution image from given low resolution image. Algorithms of single image resolution are mainly based on wavelet domain and spatial domain. Filters support to model the regularity of natural images is exploited in wavelet domain while edges of images get sharp during up sampling in spatial domain. Here single image super resolution algorithm is presented which based on both spatial and wavelet domain and take the advantage of both. Algorithm is iterative and use back projection to minimize reconstruction error. Wavelet based denoising method is also introduced to remove noise.

cs.CV↗