Adjusting Time of Flight in Ultrasound B-mode Imaging for Accurate Measurement of Fat using Image Segmentation Technique
Journal Title: Journal of ICT Research and Applications - Year 2017, Vol 11, Issue 1
Abstract
This research attempted to measure chicken intramuscular fat content using improved ultrasound B-mode images and image segmentation. Adapted B-mode imaging is proposed to increase the positioning accuracy of B-mode images with the objective to correct the phase error due to the use of predetermined ultrasonic velocity in conventional B-mode imaging. The pre-determined velocity is replaced by actual velocity measured using A-mode imaging. The positioning accuracy of adapted and conventional B-mode imaging was validated using 144 chicken samples. The adapted B-mode image had better positioning accuracy compared to a conventional B-mode image since the method used was able to detect the thickness of the chicken sample with a lower mean difference (0.036±0.034mm vs. 0.113±0.010). Both methods were then applied for measurement of intramuscular fat content. The histogram mean and the percentage of fat pixels were the B-mode image characteristics that were extracted and their correlation with the fat content, measured using the Soxhlet method, was analyzed. The properties of the adapted B-mode images correlated better with the Soxhlet-measured fat content compared to the properties of the conventional B-mode images as reflected in the correlation coefficient, r, for the histogram mean (0.357 vs. 0.129) and the percentage of fat pixels (0.406 vs. 0.289). The results indicate the potential of using ultrasound adapted B-mode imaging to measure chicken intramuscular fat.
Authors and Affiliations
Norlida Buniyamin, M. Hazwan Abdul Halim
Hybrid Neural Network and Linear Model for Natural Produce Recognition Using Computer Vision
Natural produce recognition is a classification problem with various applications in the food industry. This paper proposes a natural produce recognition method using computer vision. The proposed method uses simple feat...
Automatic Title Generation in Scientific Articles for Authorship Assistance: A Summarization Approach
This paper presents a study on automatic title generation for scientific articles considering sentence information types known as rhetorical categories. A title can be seen as a high-compression summary of a document. A...
An Application of PSV-S in Fast Development of a Real-Time DSP System
Virtual prototyping is natural in developing digital signal processing (DSP) systems using a product-service-value system (PSV-S) approach. Our DSP virtual prototyping approach consists of four development phases: (1) a...
Dynamic Path Planning for Mobile Robots with Cellular Learning Automata
In this paper we propose a new approach to path planning for mobile robots with cellular automata and cellular learning automata. We divide the planning into two stages. In the first stage, global path planning is perfor...
Improvement of Fuzzy Geographically Weighted Clustering-Ant Colony Optimization Performance using Context-Based Clustering and CUDA Parallel Programming
Geo-demographic analysis (GDA) is the study of population characteristics by geographical area. Fuzzy Geographically Weighted Clustering (FGWC) is an effective algorithm used in GDA. Improvement of FGWC has been done by...