Contrast Limited Adaptive Histogram Equalization technique (CLAHE) is a widely used form of contrast enhancement, used predominantly in enhancing medical imagery like X-rays and to enhance features in ordinary photographs. This work is aimed to understand the effectiveness of using this technique in multispectral satellite imagery and to study its effectiveness in different regions of the electromagnetic spectrum. This work also aimed in analyzing variations of spatial and spectral resolutions of a sensor affect the performance of the CLAHE technique by means of comparing quantitative parameters of the enhanced images between the sensors. A new performance parameter called Degree of Contrast Enhancement (DCE) has also been formulated so as to quantify the amount of increase/decrease in contrast between the enhanced and original images on application of the CLAHE algorithm on it. A general idea of the feature that can be enhanced in each spectral region was also studied. The results showed that the technique was most effective for shorter wavelengths when compared to longer wavelength regions. A comparative study between the CLAHE technique and the conventional global histogram equalization technique resulted in the former technique emerging superior of the two and thereby reconstructed images of better quality.
Table of Contents
1 Introduction
1.1 Global Histogram Equalization
1.2 Adaptive Histogram Equalization
1.3 Contrast Limited Adaptive Histogram Equalization
2 Data Acquisition
3 Methodology
3.1 Mean Square Error (MSE)
3.2 Peak Signal-to-Noise Ratio (PSNR)
3.3 Degree of Contrast Enhancement (DCE)
4 Comparative Analysis
5 Results and Inferences
6 Conclusions
7 References
Objectives and Research Focus
This report investigates the efficacy of the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique when applied to multispectral satellite imagery. The central research question examines how varying spatial and spectral resolutions across different sensors influence the performance of CLAHE, aimed at improving feature extraction and image quality in geospatial data.
- Evaluating the performance of CLAHE across diverse electromagnetic spectrum regions.
- Developing and applying the Degree of Contrast Enhancement (DCE) parameter.
- Comparing CLAHE against conventional Global Histogram Equalization (GHE) methods.
- Assessing the impact of sensor-specific spatial and spectral resolutions on enhancement outcomes.
Excerpt from the Book
1.3 Contrast Limited Adaptive Histogram Equalization
Contrast Limited AHE (CLAHE) developed by Pizer et al [19] [20], differs from ordinary adaptive histogram equalization in its contrast limiting [6]. This feature can also be applied to global histogram equalization, giving rise to contrast limited histogram equalization (CLHE), which is rarely used in practice.
In the case of CLAHE, the contrast limiting procedure has to be applied for each neighbourhood from which a transformation function is derived. CLAHE was developed to prevent the over-amplification of noise that adaptive histogram equalization can give rise to. This is achieved by limiting the contrast enhancement of AHE. The contrast amplification in the vicinity of a given pixel value is given by the slope of the transformation function. This is proportional to the slope of the neighbourhood cumulative distribution function (CDF) and therefore to the value of the histogram at that pixel value. CLAHE limits the amplification by clipping the histogram at a predefined value before computing the CDF. This limits the slope of the CDF and therefore of the transformation function. The value at which the histogram is clipped, the so-called clip limit, depends on the normalization of the histogram and thereby on the size of the neighbourhood region. Common values limit the resulting amplification is between 3 and 4. It is advantageous not to discard the part of the histogram that exceeds the clip limit but to redistribute it equally among all histogram bins (Fig 1.2).
Summary of Chapters
1 Introduction: Provides an overview of image enhancement techniques and introduces the motivation for applying CLAHE to satellite imagery.
2 Data Acquisition: Describes the study area and provides technical details regarding the four different sensor datasets utilized.
3 Methodology: Details the algorithmic steps for CLAHE and defines the quantitative metrics (MSE, PSNR, DCE) used for evaluation.
4 Comparative Analysis: Presents visual results of the CLAHE technique applied across various spectral bands for different sensors.
5 Results and Inferences: Analyzes the calculated quality metrics to assess the relationship between CLAHE performance and spectral resolution.
6 Conclusions: Summarizes the effectiveness of CLAHE for feature extraction and its potential as a superior alternative to GHE.
7 References: Lists the academic literature and technical documentation supporting the research.
Keywords
CLAHE, Contrast Enhancement, Multispectral Satellite Imagery, Remote Sensing, Image Processing, Histogram Equalization, Mean Square Error, PSNR, Degree of Contrast Enhancement, Spatial Resolution, Spectral Resolution, NIR Band, SWIR Band, Feature Extraction, Geospatial Data.
Frequently Asked Questions
What is the primary focus of this research report?
The report focuses on evaluating the effectiveness of the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique specifically for enhancing multispectral satellite imagery.
What are the core research themes?
The core themes include digital image processing, radiometric enhancement, performance comparison of algorithms, and the impact of different spectral bands on feature visibility.
What is the main objective of this study?
The main objective is to understand how the CLAHE technique performs across different satellite sensors and to determine its suitability for enhancing features like water bodies and shorelines.
Which quantitative methods are employed to assess image quality?
The study uses Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and a newly formulated parameter called the Degree of Contrast Enhancement (DCE).
What does the comparative analysis in the report cover?
The analysis covers the application of CLAHE to images from four different sensors (LISS III, AWiFS, Landsat 8 OLI, and Sentinel 2A MSI) across Green, Red, NIR, and SWIR bands.
Which keywords best describe this work?
Key terms include CLAHE, multispectral imagery, remote sensing, image reconstruction, and contrast enhancement metrics.
How is the Degree of Contrast Enhancement (DCE) calculated?
DCE is formulated to measure the percentage of change in the contrast ratio between the original and the enhanced images.
What conclusion does the author reach regarding the effectiveness of CLAHE?
The author concludes that CLAHE is superior to conventional Global Histogram Equalization and is highly effective for feature extraction, particularly in the NIR and SWIR spectral regions.
- Arbeit zitieren
- Vidhya Ganesh Rangarajan (Autor:in), 2016, Effectiveness of Contrast Limited Adaptive Histogram Equalization on Multispectral Satellite Imagery, München, GRIN Verlag, https://www.grin.com/document/387601
