Satellite Image Contrast Enhancement Using Fuzzy Termite Colony Optimization
01 Jan 2018-pp 115-144
TL;DR: This work has proposed a Termite Colony Optimization (TCO) algorithm based on the behavior of termites and uses the proposed algorithm and fuzzy entropy for satellite image contrast enhancement.
Abstract: Image enhancement is an essential subdomain of image processing which caters to the enhancement of visual information within an image. Researchers incorporate different bio-inspired methodologies which imitate the behavior of natural species for optimization-based enhancement techniques. Particle Swarm Optimization imitates the behavior of swarms to discover the finest possible solution in the search space. The peculiar nature of ants to accumulate information about the environment by depositing pheromones is adopted by another technique called Ant Colony Optimization. However, termites have both these characteristics common in them. In this work, the authors have proposed a Termite Colony Optimization (TCO) algorithm based on the behavior of termites. Thereafter they use the proposed algorithm and fuzzy entropy for satellite image contrast enhancement. This technique offers better contrast enhancement of images by utilizing a type-2 fuzzy system and TCO. Initially two sub-images from the input image, named lower and upper in the fuzzy domain, are determined by a type-2 fuzzy system. The S-shape membership function is used for fuzzification. Then an objective function such as fuzzy entropy is optimized in terms of TCO and the adaptive parameters are defined which are applied in the proposed enhancement technique. The performance of the proposed method is evaluated and compared with a number of optimization-based enhancement methods using several test images with several statistical metrics. Moreover, the execution time of TCO is evaluated to find its applicability in real time. Better experimental results over the conventional optimization based enhancement techniques demonstrate the superiority of our proposed methodology.
References
More filters
Proceedings Article•
06 Jul 2015TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Abstract: Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.
30,843 citations
06 Sep 2014
TL;DR: This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
Abstract: We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) [15] that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage.
4,445 citations
TL;DR: A general framework based on histogram equalization for image contrast enhancement, and a low-complexity algorithm for contrast enhancement is presented, and its performance is demonstrated against a recently proposed method.
Abstract: A general framework based on histogram equalization for image contrast enhancement is presented. In this framework, contrast enhancement is posed as an optimization problem that minimizes a cost function. Histogram equalization is an effective technique for contrast enhancement. However, a conventional histogram equalization (HE) usually results in excessive contrast enhancement, which in turn gives the processed image an unnatural look and creates visual artifacts. By introducing specifically designed penalty terms, the level of contrast enhancement can be adjusted; noise robustness, white/black stretching and mean-brightness preservation may easily be incorporated into the optimization. Analytic solutions for some of the important criteria are presented. Finally, a low-complexity algorithm for contrast enhancement is presented, and its performance is demonstrated against a recently proposed method.
794 citations
TL;DR: A new method for unsharp masking for contrast enhancement of images is presented that employs an adaptive filter that controls the contribution of the sharpening path in such a way that contrast enhancement occurs in high detail areas and little or no image sharpening occurs in smooth areas.
Abstract: This paper presents a new method for unsharp masking for contrast enhancement of images. The approach employs an adaptive filter that controls the contribution of the sharpening path in such a way that contrast enhancement occurs in high detail areas and little or no image sharpening occurs in smooth areas.
760 citations
TL;DR: In this paper, the authors considered the problem of decomposition of the probability density function of the original set into the weighted sum of the component fuzzy set densities, which is done by optimization of some functional defined over all possible fuzzy classifications.
561 citations