Histogram equalization

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

Method for generating a block-based image histogram

Abstract: A method for generating a block-based image histogram from data compressed by JPEG, MPEG-1, and MPEG-2, or uncompressed image data employing block-based linear quantization to generate histograms that include color, brightness, and edge components The edge histogram, in particular, includes the global edge features, semi-global edge features, and local edge features The global edge histogram is based on image blocks of the entire image space The local edge histogram is based on a group of edge blocks The semi-global edge histogram is based on the horizontally and the vertically grouped image blocks A method for generating block-based image histogram with color information and brightness information of image data in accordance with an embodiment of the present invention extracts feature information of an image in terms of the block and updates global histogram bins on the basis of the feature information The method for generating block-based image histogram with color information and brightness information of image data minimizes quantization error by employing linear weight and updates values of histogram bins The error that occurs at a boundary between bins of the histograms and the linear weight depends on the distance between the histogram bins

MPEG video watermarking using tensor singular value decomposition

Abstract: In this paper, we introduce a new watermarking algorithm to embed an invisible watermark into the intra-frames of an MPEG video sequence. Unlike previous methods where each video frame is marked separately, our proposed technique uses high-order tensor decomposition of videos. The key idea behind our approach is to represent a fixed number of the intra-frames as a 3D tensor with two dimensions in space and one dimension in time. Then we modify the singular values of the 3D tensor, which have a good stability and represent the video properties. The main attractive features of this approach are simplicity and robustness. The experimental results show the robustness of the proposed scheme against the most common attacks including geometric transformations, adaptive random noise, low pass filtering, histogram equalization, frame dropping, frame swapping, and frame averaging.

Brain Tumour Detection Using Unsupervised Learning Based Neural Network

Abstract: The task of MRI (Magnetic resonance Imaging) brain tumor images Classification is difficult due to the variance and complexity of tumors. This paper presents an unsupervised learning based Neural Network technique for the classification of the magnetic resonance human brain images. Brain tumour diagnosis requires a detailed histological analysis, which involves invasive surgery that can be painful and can cause discomfort to patients. In this paper, the brain tumour diagnostic procedure is divided into the following phases. The first phase comprises of image pre-processing which includes histogram equalization, edge detection, noise filtering, thresholding etc. In second phase, the features of the MR brain image are extracted using Independent Component Analysis (ICA). In third phase, brain tumour diagnosis is performed using Self Organized Map (SOM). Finally, a kmeans clustering algorithm is applied to segment the brain into different tissues. Classification results on a variety of MR images for different pathologies indicate this technique to be promising.

No-Reference Quality Assessment of Contrast-Distorted Images using Contrast Enhancement.

Abstract: No-reference image quality assessment (NR-IQA) aims to measure the image quality without reference image. However, contrast distortion has been overlooked in the current research of NR-IQA. In this paper, we propose a very simple but effective metric for predicting quality of contrast-altered images based on the fact that a high-contrast image is often more similar to its contrast enhanced image. Specifically, we first generate an enhanced image through histogram equalization. We then calculate the similarity of the original image and the enhanced one by using structural-similarity index (SSIM) as the first feature. Further, we calculate the histogram based entropy and cross entropy between the original image and the enhanced one respectively, to gain a sum of 4 features. Finally, we learn a regression module to fuse the aforementioned 5 features for inferring the quality score. Experiments on four publicly available databases validate the superiority and efficiency of the proposed technique.