A comparative study on improvement of image compression method using hybrid of DCT and DWT techniques with huffman encoding

• Main Author: Anwar Hussin, Mumtaz
• Format: Thesis
• Language: English; English; English
• Published: 2021
• Subjects: T Technology (General); TA1501-1820 Applied optics. Photonics
• Online Access: http://eprints.uthm.edu.my/6455/1/24p%20MUMTAZ%20YAHYA%20NASSER%20NASSAR.pdf; http://eprints.uthm.edu.my/6455/2/MUMTAZ%20YAHYA%20NASSER%20NASSAR%20COPYRIGHT%20DECLARATION.pdf; http://eprints.uthm.edu.my/6455/3/MUMTAZ%20YAHYA%20NASSER%20NASSAR%20WATERMARK.pdf; http://eprints.uthm.edu.my/6455/
• Institution: Universiti Tun Hussein Onn Malaysia

Image is an important media used to visualize or represent a message in daily conversation between users device. Nowadays, there are many application that involve image processing such as security system, communication system and medical system where images are processed digitally. Image is mainly known for its large data capacity especially high resolution image. Thus, image compression is important to reduce storage size and achieve specific application goals. In this research, hybrid of Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Huffman compression technique is proposed. Stand-alone technique of DCT, DWT and Huffman are execute before hybrid all techniques together. Besides, the performance in determining the quality of image, compression ratio and computing time are carefully observed by evaluating the result of Mean Square Error (MSE), Power Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), compression ratio and time of compression and decompression. It is found that the proposed hybrid technique able to reduce storage size with 3.72:1 compression ratio and short computing time with 5 second. The quality of image is slightly reduce compared to original image which are calculated based on MSE, PSNR and SSIM value with 52.74, 30.92 dB and 0.90, respectively. In conclusion, DWT technique has the ability in compressing image size within short time while DCT and Huffman are able to reduce data loss during compression and maintaining good quality of image. Therefore, DCT, DWT and Huffman method are combined together to support each other in producing good performance.