Histogram equalization

About: Histogram equalization is a research topic. Over the lifetime, 5755 publications have been published within this topic receiving 89313 citations.

Content-based image retrieval using multiresolution histogram representation

Abstract: We present two new approaches based on color histogram indexing for content-based retrieval of image databases. Since the high computational complexity has been one of the main barriers towards the use of similarity measures such as histogram intersection in large databases, we propose a hierarchical indexing scheme where computationally efficient features are used to subset the image before more sophisticated techniques are applied for precise retrieval. The use of histograms at different color resolutions as filtering and matching features in a hierarchical scheme is studied. In the second approach, a multiresolution representation of the histogram using the indices and signs of its largest wavelet coefficients is examined. Excellent results have been observed using the latter method.

Dense Prediction and Local Fusion of Superpixels: A Framework for Breast Anatomy Segmentation in Ultrasound Image With Scarce Data

Abstract: Segmentation of the breast ultrasound (BUS) image is an important step for subsequent assessment and diagnosis of breast lesions. Recently, Deep-learning-based methods have achieved satisfactory performance in many computer vision tasks, especially in medical image segmentation. Nevertheless, those methods always require a large number of pixel-wise labeled data that is expensive in medical practices. In this study, we propose a new segmentation method by dense prediction and local fusion of superpixels for breast anatomy with scarce labeled data. First, the proposed method generates superpixels from the BUS image enhanced by histogram equalization, a bilateral filter, and a pyramid mean shift filter. Second, using a convolutional neural network (CNN) and distance metric learning-based classifier, the superpixels are projected onto the embedding space and then classified by calculating the distance between superpixels’ embeddings and the centers of categories. By using superpixels, we can generate a large number of training samples from each BUS image. Therefore, the problem of the scarcity of labeled data can be better solved. To avoid the misclassification of the superpixels, $K$ -nearest neighbor (KNN) is used to reclassify the superpixels within every local region based on the spatial relationships among them. Fivefold cross-validation was taken and the experimental results show that our method outperforms several often used deep-learning methods under the condition of the absence of a large number of labeled data (48 BUS images for training and 12 BUS images for testing).

No reference color image quality measures

Abstract: Color image quality assessment is essential in evaluating the performance of color image enhancement and retrieval algorithms. Much effort has been made in recent years to develop objective image quality metrics that correlate with perceived quality measurements. Unfortunately, only limited success has been achieved [1]. In this paper we present: a) a new contrast based grayscale image quality measure: Root Mean Enhancement (RME); b) a color RME contrast measure CRME which explores the three dimensional contrast relationships of the RGB color channels; c) a color measure Color Qiality Enhancement (CQE) which is based on the linear combination of colorfulness, sharpness and contrast. Computer simulations show that the new measures may help to evaluate color image quality and choose the optimal operating parameters in color image processing systems. We demonstrate the effectiveness of the presented measures by using the TID2008 database. We also compare the presented measures with subjective evaluation Mean Opinion Score (MOS). Experimental results show good correlations between the presented measures and MOS.