Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction
Noor Islam S. Mohammad
TL;DR
This work targets deterministic, reproducible preprocessing for high-resolution images to support reliable low-level vision tasks. It presents a modular pipeline that integrates eight-level grayscale quantization, luminance-based color enhancement (YCrCb) and HSV brightness adjustment, 3×3 sharpening, a bidirectional transformation framework, and comprehensive geometric feature extraction (Canny, Hough, Harris, and morphological windowing). Key findings show luminance-based histogram equalization reduces color artifacts while boosting contrast, forward/backward pipeline similarities around 76% and 75%, and robust cue isolation with angular alignment near 51.5°, underscoring strong practical potential for real-time analysis and hybrid integration with learning-based systems. The results demonstrate a deterministic preprocessing foundation suitable for embedded and real-time vision tasks, with clear avenues for adaptive and deep learning extensions to improve robustness and generalization across diverse imaging conditions.
Abstract
This study introduces a modular framework for spatial image processing, integrating grayscale quantization, color and brightness enhancement, image sharpening, bidirectional transformation pipelines, and geometric feature extraction. A stepwise intensity transformation quantizes grayscale images into eight discrete levels, producing a posterization effect that simplifies representation while preserving structural detail. Color enhancement is achieved via histogram equalization in both RGB and YCrCb color spaces, with the latter improving contrast while maintaining chrominance fidelity. Brightness adjustment is implemented through HSV value-channel manipulation, and image sharpening is performed using a 3 * 3 convolution kernel to enhance high-frequency details. A bidirectional transformation pipeline that integrates unsharp masking, gamma correction, and noise amplification achieved accuracy levels of 76.10% and 74.80% for the forward and reverse processes, respectively. Geometric feature extraction employed Canny edge detection, Hough-based line estimation (e.g., 51.50° for billiard cue alignment), Harris corner detection, and morphological window localization. Cue isolation further yielded 81.87\% similarity against ground truth images. Experimental evaluation across diverse datasets demonstrates robust and deterministic performance, highlighting its potential for real-time image analysis and computer vision.