Region of Interest Based Compression of Medical Images Using Vector Quantization

Compressive sensing is one of teh cost effective solution towards performing compression of heavier form of signals. We reviewed the existing research contribution towards compressive sensing to find that existing system doesnt offer any form of optimization for which reason the signal are superiorly compressed but at the cost of enough resources. Therefore, we introduce a framework that optimizes the performance of the compressive sensing by introducing 4 sequential algorithms for performing Random Sampling, Lossless Compression for region-of-interest, Compressive Sensing using transform-based scheme, and optimization. The contribution of proposed paper is a good balance between computational efficiency and quality of reconstructed medical image when transmitted over network with low channel capacity. The study outcome shows that proposed system offers maximum signal quality and lower algorithm processing time in contrast to existing compression techniuqes on medical images.

Download Full-text

OPTIMASI ALGORITMA LEARNING VECTOR QUANTIZATION (LVQ) DALAM PENGKLASIFIKASIAN CITRA DAGING SAPI DAN DAGING BABI BERBASIS GLCM DAN HSV

Simetris Jurnal Teknik Mesin Elektro dan Ilmu Komputer ◽

10.24176/simet.v9i1.1943 ◽

2018 ◽

Vol 9 (1) ◽

pp. 1-10

Author(s):

Usman Sudibyo ◽

Desi Purwanti Kusumaningrum ◽

Eko Hari Rachmawanto ◽

Christy Atika Sari

Keyword(s):

Vector Quantization ◽

Region Of Interest ◽

Learning Vector Quantization ◽

Gray Level ◽

Minimum Error ◽

Occurrence Matrix

Meningkatnya kebutuhan daging sapi, berdampak pada harga daging sapi. Harga daging sapi yang terus menerus mengalami kenaikan, tentunya menyebabkan penurunan penjualan daging sapi. Untuk mengantisipasi hal tersebut, maka beberapa pedagang mencampurkan daging sapi dengan daging babi. Dipilihnya daging babi, karena harga daging babi lebih murah dan warna serta tekstur daging babi yang mirip dengan daging sapi. Secara kasat mata daging sapi dan daging babi sulit untuk dibedakan bagi orang awam. Oleh karena itu, perlu adanya sistem yang dapat membedakan kedua daging. Penelitian ini menggunakan metode klasifikasi untuk membedakan kedua daging. Metode klasifikasi menggunakan algoritma Learning Vector Quantization. Dan penelitian ini memiliki tiga tahapan utama seperti preprocessing, segmentasi warna, ekstraksi fitur, dan klasifikasi. Preprocessing digunakan untuk mendapatkan Region of Interest (ROI) dengan memotong citra dan mengubah ukuran citra. Segmentasi warna menggunakan metode HSV untuk mendapatkan kedalaman warna citra dan ekstraksi fitur mengguakan Gray Level Co-occurrence Matrix (GLCM) untuk mendapatkan fitur dari kontras, korelasi, energi, dan homogenitas. Hasil klasifikasi dengan algoritma LVQ mendapatkan akurasi tertinggi 76,25%. Algoritma telah diuji dengan MSE untuk mengetahui minimum error dan PSNR digunakan sebagai pengukuran kualitas citra pengolahan.

Download Full-text

Image Compression Using Different Vector Quantization Algorithms and Its Comparison

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.i8165.078919 ◽

2019 ◽

Vol 8 (9) ◽

pp. 3459-3488

Keyword(s):

Image Compression ◽

Vector Quantization ◽

Data Transfer ◽

Medical Images ◽

Smooth Transition ◽

Discrete Wavelet ◽

Fcm Algorithm ◽

Codebook Design ◽

Fuzzy C Means Clustering ◽

Fuzzy Partitions

Image compression techniques are presented in this paper which can be used for storage and transmission of digital lossy images. It is mostly important in both multimedia and medical field to store huge database and data transfer. Medical images are used for diagnosis purposes. So, vector quantization is a novel method for lossy image compression that includes codebook design, encoding and decoding stages. Here, we have applied different lossy compression techniques like VQ-LBG (Vector quantization- Linde, Buzo and Gray algorithm), DWT-MSVQ (Discrete wavelet transform-Multistage Vector quantization), FCM (Fuzzy c-means clustering) and GIFP-FCM (Generalized improved fuzzy partitions-FCM) methods on different medical images to measure the qualities of compression. GIFP-FCM is an extension of classical FCM and IFP-FCM (Improved fuzzy partitions FCM) algorithm with a purpose to reward hard membership degree. The presentation is assessed based on the effectiveness of grouping output. In this method, a new objective function is reformulated and minimized so that there is a smooth transition from fuzzy to crisp mode. It is fast, easy to implement and has rapid convergence. Thus, the obtained results show that GIFP-FCM algorithm gives better PSNR performance, high CR (compression ratio), less MSE (Mean square error) and less distortion as compared to other above used methods indicating better image compression.

Download Full-text

An Intelligent cluster-based segmentation using Wavelet Features:Application to Medical Images

10.54294/1xmz73 ◽

2010 ◽

Author(s):

Thavavel V ◽

JafferBasha J

Keyword(s):

Medical Images ◽

Automatic Segmentation ◽

A Priori ◽

User Interaction ◽

Region Of Interest ◽

Feature Space ◽

Discrete Wavelet ◽

Wavelet Frames ◽

Translation Invariant ◽

Spherical Coordinate

Segmentation forms the onset for image analysis especially for medical images, making any abnormalities in tissues distinctly visible. Possible application includes the detection of tumor boundary in SPECT, MRI or electron MRI (EMRI). Nevertheless, tumors being heterogeneous pose a great problem when automatic segmentation is attempted to accurately detect the region of interest (ROI). Consequently, it is a challenging task to design an automatic segmentation algorithm without the incorporation of ‘a priori’ knowledge of an organ being imaged. To meet this challenge, here we propose an intelligence-based approach integrating evolutionary k-means algorithm within multi-resolution framework for feature segmentation with higher accuracy and lower user interaction cost. The approach provides several advantages. First, spherical coordinate transform (SCT) is applied on original RGB data for the identification of variegated coloring as well as for significant computational overhead reduction. Second the translation invariant property of the discrete wavelet frames (DWF) is exploited to define the features, color and texture using chromaticity of LL band and luminance of LH and HL band respectively. Finally, the genetic algorithm based K-means (GKA), which has the ability to learn intelligently the distribution of different tissue types without any prior knowledge, is adopted to cluster the feature space with optimized cluster centers. Experimental results of proposed algorithm using multi-modality images such as MRI, SPECT, and EMRI are presented and analyzed in terms of error measures to verify its effectiveness and feasibility for medical applications.

Download Full-text