Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn Finding Gray Pixels
102
0
0.0
(
0
)
Added by
Yanlin Qian
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We propose a novel grayness index for finding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation. The grayness index, GI in short, is derived using the Dichromatic Reflection Model and is learning-free. GI allows to estimate one or multiple illumination sources in color-biased images. On standard single-illumination and multiple-illumination estimation benchmarks, GI outperforms state-of-the-art statistical methods and many recent deep methods. GI is simple and fast, written in a few dozen lines of code, processing a 1080p image in ~0.4 seconds with a non-optimized Matlab code.
rate research
Read More
In the real world, a scene is usually cast by multiple illuminants and herein we address the problem of spatial illumination estimation. Our solution is based on detecting gray pixels with the help of flash photography. We show that flash photography significantly improves the performance of gray pixel detection without illuminant prior, training data or calibration of the flash. We also introduce a novel flash photography dataset generated from the MIT intrinsic dataset.
In an effort to interpret black-box models, researches for developing explanation methods have proceeded in recent years. Most studies have tried to identify input pixels that are crucial to the prediction of a classifier. While this approach is meaningful to analyse the characteristic of blackbox models, it is also important to investigate pixels that interfere with the prediction. To tackle this issue, in this paper, we propose an explanation method that visualizes undesirable regions to classify an image as a target class. To be specific, we divide the concept of undesirable regions into two terms: (1) factors for a target class, which hinder that black-box models identify intrinsic characteristics of a target class and (2) factors for non-target classes that are important regions for an image to be classified as other classes. We visualize such undesirable regions on heatmaps to qualitatively validate the proposed method. Furthermore, we present an evaluation metric to provide quantitative results on ImageNet.
Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models. However, the existing methods can only interpret some specific decision logic on individual or a small number of images. To facilitate human understandability and generalization ability, it is important to develop representative interpretations that interpret common decision logics of a CNN on a large group of similar images, which reveal the common semantics data contributes to many closely related predictions. In this paper, we develop a novel unsupervised approach to produce a highly representative interpretation for a large number of similar images. We formulate the problem of finding representative interpretations as a co-clustering problem, and convert it into a submodular cost submodular cover problem based on a sample of the linear decision boundaries of a CNN. We also present a visualization and similarity ranking method. Our extensive experiments demonstrate the excellent performance of our method.
We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering. The method, called Mean Shifted Grey Pixel -- MSGP, is based on the observation: true-gray pixels are aligned towards one single direction. Our solution is compact, easy to compute and requires no training. Experiments on two real-world benchmarks show that the proposed approach outperforms state-of-the-art methods in the camera-agnostic scenario. In the setting where the camera is known, MSGP outperforms all statistical methods.
Edge detection is an important field in image processing. Edges characterize object boundaries and are therefore useful for segmentation, registration, feature extraction, and identification of objects in a scene. In this paper, an approach utilizing an improvement of Baljit and Amar method which uses Shannon entropy other than the evaluation of derivatives of the image in detecting edges in gray level images has been proposed. The proposed method can reduce the CPU time required for the edge detection process and the quality of the edge detector of the output images is robust. A standard test images, the real-world and synthetic images are used to compare the results of the proposed edge detector with the Baljit and Amar edge detector method. In order to validate the results, the run time of the proposed method and the pervious method are presented. It has been observed that the proposed edge detector works effectively for different gray scale digital images. The performance evaluation of the proposed technique in terms of the measured CPU time and the quality of edge detector method are presented. Experimental results demonstrate that the proposed method achieve better result than the relevant classic method.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
