Single Pixel Spectral Color Constancy

In order to fully utilize potential feature information of RGB-D images, current popular algorithms mainly use convolutional neural network (CNN) to execute both feature extraction and classification. Such methods could achieve impressive results but usually on the basis of an extremely huge and complex network. What’s more, since the fully connected layers in CNN form a classical neural network classifier, which is trained by gradient descent-based implementations, the generalization ability is limited and sub-optimal. To address these problems, this paper introduce a multi-view CNN-SPMP-RNN-ELM (MCSPMPR-ELM) model for RGB-D object recognition, which combines the power of MCSPMPR and fast training of ELM. It uses the MCSPMPR algorithm to extract discriminative features from raw RGB images and depth images separately. Then the abstracted features are fed to a nonlinear ELM classifier, which leads to better generalization performance with faster learning speed. At last, co-training is employed to learn from the unlabeled data using the two distinct feature sets by semi-supervised learning method. Experimental results on widely used RGB-D object datasets show that our method achieves competitive performance compared with other state-of-the-art algorithms specifically designed for RGB-D data.

Beef carcass grading plays a pivotal role in determining market value and consumer preferences. While traditional visual inspection by experts remains the industry standard, it suffers from subjectivity and inconsistencies, particularly in high-throughput slaughterhouse environments. To address these limitations, we propose a one-stage automated grading model based on EfficientViT, a lightweight vision transformer architecture. Unlike conventional two-stage methods that require prior segmentation of the loin region, our model directly predicts beef quality grades from raw RGB images, significantly simplifying the pipeline and reducing computational overhead. We evaluate the proposed model against representative convolutional neural networks (VGG-16, ResNeXt-50, DenseNet-121) as well as two-stage combinations of segmentation and classification models. Experiments were conducted on a publicly available beef carcass dataset consisting of over 77,000 labeled images. EfficientViT achieves the highest accuracy (98.46%) and F1-score (0.9867) among all evaluated models while maintaining low inference latency (3.92 ms) and compact parameter size (36.4 MB). In particular, it outperforms CNNs in predicting the top grade (1++), where global visual patterns such as marbling distribution are crucial. Furthermore, we employ Grad-CAM and attention map visualizations to analyze the model’s focus regions and demonstrate that EfficientViT captures holistic contextual features better than CNNs. The model also exhibits robustness across varying loin area proportions. Our findings suggest that EfficientViT is not only accurate but also efficient and interpretable, making it a strong candidate for real-time industrial applications in beef quality grading.

Deep learning based approaches proved to be dramatically effective to address many computer vision applications, including recognition in the wild. It has been extensively demonstrated that methods exploiting Deep Convolutional Neural Networks (DCNN) are powerful enough to overcome to a great extent many problems that negatively affected computer vision algorithms based on hand-crafted features. These problems include variations in illumination, pose, expression and occlusion, to mention some. The DCNNs excellent discriminative power comes from the fact that they learn low-and high-level representations directly from the raw image data. Considering this, it can be assumed that the performance of a DCNN are influenced by the characteristics of the raw image data that are fed to the network. In this work, we evaluate the effect of different bounding box dimensions, alignment, positioning and data source on face recognition using DCNNs, and present a thorough evaluation on two well known, public DCNN architectures.

Temporal color constancy (TCC) is a recent research direction that uses multiple temporally correlated images (e.g., frames in a video) to perform illuminant estimation. Compared to traditional single-frame color constancy methods, temporal or multi-frame methods can leverage the additional temporal information inherent in sequences, which makes them naturally suitable for processing videos. In this paper, we present a hybrid framework called Fusion Temporal Color Constancy that combines classical color constancy algorithms, convolutional neural networks (CNN), and recurrent neural networks (RNN) for the task of TCC. Experimental results show that our hybrid approach achieves state-of-the-art accuracy on several publicly available multi-frame and single-frame color constancy benchmarks.

713 A New EUS Imaging Diagnosis for Pancreatic Cancer: A Pilot Study of Differential Diagnosis Between Chronic Pancreatitis and Pancreatic Cancer Based on the Quantitative Analysis With New Technology Using Raw Image

The color constancy is a procedure that measures the influence of different light sources on a digital image. The goal of the computational color constancy is to account for the effect of the illuminate.Many traditional methods such as Grey-world method, Max RGB and learning-based method were used to measure the color constancy of digital images affected by light source. All these methods have an obvious disadvantage that the light source across the scene is spectrally uniform. This assumption is often violated as there might be more than one light source illuminating the scene. This paper has proposed a modified edge based color constancy using non local means and the adaptive histogram equalization. The proposed algorithm has ability to reduce the uneven illuminate problem of edge based color constancy and also non-local means has produced sharper results. The proposed algorithm is designed and implemented in the MATLAB using image processing toolbox. The comparison among the modified edge based color constancy and the edge based color constancy has shown that the proposed algorithm is quite effective over the available methods.

The cooperative manipulators can execute a wide range of tasks, such as carrying large or heavy payloads, which are difficult for a single manipulator. Dual arm manipulators are in typically operative configuration to mimic human, which are of highly flexibility and dexterity. In this paper, we propose a novel coarse-to-fine deep learning model along with investigating the grasp prior loss based on the well-known antipodal force-closure property. The proposed deep learning model predicts the contact configurations in grasping over-loaded and over-sized objects for dual arm manipulators directly from raw RGB images. We first apply detection network to locate the coarse bounding box of objects, further apply a fine-predicting network on the bounding box clipped images to precisely generate two contact configurations via minimizing regression loss and the antipodal grasp prior loss. Extensive experimental results under dense clutter and occlusion strongly demonstrate the effectiveness and robustness of the proposed method.

Coded aperture snapshot spectral imaging (CASSI) has been demonstrated as a feasible solution to recover a 3D hyperspectral image by using a single 2D measurement. In this paper, we propose a new hybrid camera design for CASSI to capture high quality hyperspectral images while maintaining the snapshot advantage. Specifically, we employ a complementary RGB camera in conjunction with the CASSI system. The recorded RGB image can provide reliable spectral clue of the scene. By combining the coded hyperspectral information from the CASSI branch and the uncoded color information from the RGB branch, hyperspectral images can be reconstructed with high fidelity. Furthermore, by conducting demosaicing on the raw RGB image as a preprocessing procedure, even better performance can be achieved. Both theoretical analysis and simulation results show improved accuracy of the proposed method compared to the state-of-the-arts.

This paper addresses the critical task of tobacco curing stage discrimination by leveraging image color features. Considering the computational constraints of typical curing barn environments, we propose a novel, non-deep learning method based on multi-channel fused features and Fisher Vector encoding. The method extracts heterogeneous, quality-sensitive features across multiple perceptually relevant color spaces, aggregating them into a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{4 5}$</tex>-channel feature map group. A Gaussian Mixture Model is trained on these features, and the image is subsequently represented by its Fisher Vector relative to this GMM. A Support Vector Regression model then maps this representation to a curing stage prediction. Experimental results demonstrate the method's superior performance and robustness compared to a baseline using raw RGB images. On a proprietary tobacco leaf image dataset, it achieves near-perfect accuracy for distinct stages and maintains high accuracy even with severely limited training data. The method significantly outperforms the baseline, proving its enhanced capability in capturing discriminative color features and its strong potential for practical, resource-constrained deployment in intelligent curing systems.

Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB image. The VMFM method requires no additional inputs, e.g. trimap or known background. We reformulate foreground matting as a self-supervised multi-modality problem: factor each input image into estimated depth map, segmentation mask, and interaction heatmap using three auto-encoders. In order to fully utilize the characteristics of each modality, we first train a dual encoder-to-decoder network to estimate the same alpha matte. Then we introduce a self-supervised method: Complementary Learning(CL) to predict deviation probability map and exchange reliable gradients across modalities without label. We conducted extensive experiments to analyze the effectiveness of each modality and the significance of different components in complementary learning. We demonstrate that our model outperforms the state-of-the-art methods.

Work-related musculoskeletal disorders (WMSDs) are a leading concern in industrial ergonomics, often stemming from sustained non-neutral postures and repetitive tasks. This paper presents a vision-based framework for real-time, frame-level ergonomic risk classification using a lightweight Vision Transformer (ViT). The proposed system operates directly on raw RGB images without requiring skeleton reconstruction, joint angle estimation, or image segmentation. A single ViT model simultaneously classifies eight anatomical regions, enabling efficient multi-label posture assessment. Training is supervised using a multimodal dataset acquired from synchronized RGB video and full-body inertial motion capture, with ergonomic risk labels derived from RULA scores computed on joint kinematics. The system is validated on realistic, simulated industrial tasks that include common challenges such as occlusion and posture variability. Experimental results show that the ViT model achieves state-of-the-art performance, with F1-scores exceeding 0.99 and AUC values above 0.996 across all regions. Compared to previous CNN-based system, the proposed model improves classification accuracy and generalizability while reducing complexity and enabling real-time inference on edge devices. These findings demonstrate the model's potential for unobtrusive, scalable ergonomic risk monitoring in real-world manufacturing environments.

The spectrum distribution of the light source between scenes is usually uniform in all scenes lit by a given light source per the color constancy assumption. Nonuniform spectrum distribution results in pictures with different color temperatures in different lighting conditions. With the conventional automated white balance method, the results under different degrees of color cast are inconsistent. To resolve this, a new automated white balance algorithm is proposed to achieve uniformity in images with color cast caused by color temperature variations. The proposed method features the selection of near-white points through automated regression and the dynamic adjustment of the color components’ weights. Finally, white balance is implemented according to the selected near-white points with various percentages. The proposed method can effectively select the appropriate white reference point of the image scene under different color temperatures, so that the adjusted results of the method under different color temperatures are close. The first major contribution of this study is the minimization of differences of continual color temperature images with different color temperatures and the achievement of favorable visual effects. The second contribution is the superior outcomes yielded by the proposed method in the visualization and quantification of data compared with those from the existing methods. The experimental results demonstrate that this method yields favorable results in the improvement of experiments with continual different color temperatures. The images at various color temperatures are adjusted to approach real-world color temperatures. In addition, this method provides superior color constancy preservation to other methods.

Mobile robots frequently operate in rough, uneven terrain. One way for them to identify easier to traverse paths is to use deep learning methods, such as a convolutional neural network (CNN). It is not clear, however, what input should be provided to the CNN to best enable it to classify different terrain. In this study, we investigate and compare several input formats for improving terrain classification using a CNN. All experiments take place in simulation, where we have complete control over terrain (e.g., shapes and textures) and information about our robot. Our experiments lead us to the following conclusions: (1) input formats should prefer grayscale over color images as color has a tendency to overfit the training data and (2) disparity maps also improve classification compared with raw image data. These results can be used to improve the performance of terrain classification; particularly as they apply to transformable-wheel robots.

The evaluation of input device spectral sensitivity is often performed in terms of colorimetric quality and potential noise caused by overlaps among spectral sensitivities. Based on the assumption that the white balancing function should aim at color constancy rather than chromatic adaptation, we have proposed a new measure to evaluate camera sensitivities. We measure how accurate camera estimates the colors of typical objects under a standard light source from the ones under different light sources. Firstly, we apply these three evaluation measures, which are colorimetric error, noise amount, and newly proposed color constancy prediction error (CCPE), to eight sets of camera sensitivities. Thus it is found that sensitivity set of a conventional TV camera performs better CCPE than the E-H-P primaries. Secondly, we optimized primary conversion with a linear diagonal matrix transform, a. k. a. von Kries transformation, in order to minimize CCPE. The sensitivity obeying the Luther condition does not necessarily perform the best while the conventional TV camera sensitivity gives the best result. Lastly, we evaluate the optimized results with spectral reflectance database for several light sources including fluorescent lamps. We found that a linear combination of color rendering properties (Ra) of light sources and reciprocal color temperature difference from the standard light source well estimates CCPE.

Using convolutional neural network models illumination estimation according to light colors