Fuzzy-Contextual Contrast Enhancement

Abstract

This paper presents contrast enhancement algorithms based on fuzzy contextual information of the images. We introduce fuzzy similarity index and fuzzy contrast factor to capture the neighborhood characteristics of a pixel. A new histogram, using fuzzy contrast factor of each pixel is developed, and termed as the fuzzy dissimilarity histogram (FDH). A cumulative distribution function (CDF) is formed with normalized values of FDH and used as a transfer function to obtain the contrast enhanced image. The algorithm gives good contrast enhancement and preserves the natural characteristic of the image. In order to develop a contextual intensity transfer function, we introduce a fuzzy membership function based on fuzzy similarity index and coefficient of variation of the image. The contextual intensity transfer function is designed using the fuzzy membership function to achieve final contrast enhanced image. The overall algorithm is referred as the fuzzy contextual contrast-enhancement (FCCE) algorithm. The proposed algorithms are compared with conventional and state-of-art contrast enhancement algorithms. The quantitative and visual assessment of the results is performed. The results of quantitative measures are statistically analyzed using t-test. The exhaustive experimentation and analysis show the proposed algorithm efficiently enhances contrast and yields in natural visual quality images.

Contrast Enhancement Using Sensitivity Model-Based Sigmoid Function

“…550 test images were taken from three datasets in [41]- [43] for a comparison of the proposed method (sensitivity model-based sigmoid curve, SMSC) with weighted adaptive histogram equalization (WAHE) [1], contextual and variational contrast (CVC) [20], layered difference representation (LDR) [11], adaptive gamma correction (AGC) [23], fuzzy-contextual contrast enhancement (FCCE) [45], two sigmoid function-based methods [46], [47], and some recent direct methods [38], [48], [49]. The conventional methods are implemented by employing the default parameters provided by the authors.…”

“…It is noteworthy that the proposed method achieved higher enhancement performance, lower mean-brightness change, and less image distortion with lower computational complexity at the same time compared with CVC, LDR, and FCCE which construct their transformation functions by using the FIGURE 7. Enhanced images of the ''Tank'' image from the USC-SIPI database [42]: (a) input image, (b) NPEA [38], (c) LSCN [48], (d) RSIE [49], (e) WAHE [1], (f) CVC [20], (g) LDR [11], (h) AGC [23], (i) FCCE [45], (j) CESF [46], (k) EACE [47], and (l) proposed method.…”

“…Although an image has higher quantitative measures than other images, its subjective visual quality may not always superior accordingly [11], [45]. For this reason, this section presents examples of enhanced images for a subjective assessment of their visual qualities and conducts a comparative analysis of the properties of the proposed method and the conventional methods.…”

“…Since HE shifts the mean brightness of the enhanced image to the middle gray level, researchers have separated the image histogram into multiple sub-histograms and performed HE on each sub-histogram individually [12]- [16]. For detail preservation, recent indirect methods utilize a two-dimensional (2D) histogram [19]- [21], [51], [52] or fuzzy contextual information [45], [53] to build the image histogram which gives more weight to the pixels in texture regions. Compared with other indirect methods, these methods achieve better enhancement performance and less information loss.…”

A novel brain image enhancement method based on nonsubsampled contourlet transform

“…In this section, the images from the databases http://brainweb.bic.mni.mcgill.ca/brainweb/, http://ctisus.com and http://radpod.org are tested to demonstrate the effectiveness of the proposed technique. We compare the performance of the proposed method with several other state‐of‐the‐art approaches, namely HE, BPDFHE, general framework based on HE for image contrast enhancement (WAHE), contextual and variational contrast enhancement (CVC), layered difference representation (LDR), dominant orientation‐based texture HE (DOTHE) and edge‐based texture HE (ETHE) . The objective as well as subjective assessment are selected to demonstrate the enhanced effect.…”