Deep Learning, Machine Learning -- Digital Signal and Image Processing: From Theory to Application
Weiche Hsieh, Ziqian Bi, Junyu Liu, Benji Peng, Sen Zhang, Xuanhe Pan, Jiawei Xu, Jinlang Wang, Keyu Chen, Caitlyn Heqi Yin, Pohsun Feng, Yizhu Wen, Tianyang Wang, Ming Li, Jintao Ren, Xinyuan Song, Qian Niu, Silin Chen, Ming Liu
TL;DR
<3-5 sentence high-level summary>This paper surveys core digital signal and image processing techniques with emphasis on classic transforms (DTFT, DFT/FFT, Z-transform) and their application to filtering, sampling-rate conversion, and multirate systems, then extends these concepts to digital image processing (acquisition, quantization, color spaces, spatial/frequency-domain enhancement, restoration, segmentation, and edge detection). It presents practical Python-based examples for plotting signals, computing transforms, designing FIR/IIR filters, and performing image processing tasks such as histogram equalization, thresholding, and frequency-domain filtering. The work highlights concrete methods for analyzing and improving signals and images, including stability/causality considerations, polyphase multirate structures, and standard restoration techniques (inverse/Wiener/regularization), underscoring how these tools support real-time, AI-assisted computer vision and multimedia applications. Overall, it provides a practical, theory-grounded toolkit for engineers and researchers to implement robust DSP and DIP pipelines using Python, with clear pathways from fundamental theory to application.
Abstract
Digital Signal Processing (DSP) and Digital Image Processing (DIP) with Machine Learning (ML) and Deep Learning (DL) are popular research areas in Computer Vision and related fields. We highlight transformative applications in image enhancement, filtering techniques, and pattern recognition. By integrating frameworks like the Discrete Fourier Transform (DFT), Z-Transform, and Fourier Transform methods, we enable robust data manipulation and feature extraction essential for AI-driven tasks. Using Python, we implement algorithms that optimize real-time data processing, forming a foundation for scalable, high-performance solutions in computer vision. This work illustrates the potential of ML and DL to advance DSP and DIP methodologies, contributing to artificial intelligence, automated feature extraction, and applications across diverse domains.