ABSTRACT
Nowadays, dietary assessment becomes the emerging system for evaluating the person’s food intake. In this paper, the multiple hypothesis image segmentation and feed-forward neural network classifier are proposed for dietary assessment to enhance the performance. Initially, the segmentation is applied to input image which is used to determine the regions where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the significant feature of food items is extracted by the global feature and local feature extraction method. After the features are obtained, the classification is performed for each segmented region using feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food area volume and (ii) calorie and nutrition measure based on mass value. The outcome of the proposed method attains 96% of accuracy value which provides the better classification performance.
Disclosure statement
No potential conflict of interest was reported by the authors.
Note
All images can be accessed through the following digital repositories:
Images in Figure 2
http://iranianclinic.com/index.aspx?fkeyid=&siteid=140&pageid=3167
http://www.agingservicesmenh.org/guide/top-20-foods-for-young-and-beautiful-skin/
http://www.lovebakesgoodcakes.com/2015/07/rainbow-fruit-salad-honey-citrus-dressing.html?m=1
Image in Figure 3
http://www.irishhealth.com/article.html?id=23201
Image in Figure 4
http://www.differencebetween.info/difference-between-brinjal-and-eggplant
Images in , and
A. http://pragmaticobotsunite.com/friday-open-thread-african-american-winemakers-ii/
B. http://www.differencebetween.info/difference-between-brinjal-and-eggplant
C. http://www.agingservicesmenh.org/guide/top-20-foods-for-young-and-beautiful-skin/
D. http://www.lovebakesgoodcakes.com/2015/07/rainbow-fruit-salad-honey-citrus-dressing.html?m=1
Notes on contributors
S. Jasmine Minija received her M.Phil (Computer Science) degree in 2014 from Mother Teresa Women’s University, Kodaikanal and M.Sc degree in 2013 from Manonmaniam Sundaranar University, Tirunelveli. Now she is doing doctoral research under Manonmaniam Sundaranar University, Tirunelveli. Her interested research areas are Image Segmentation and classification.
W. R. Sam Emmanuel received his doctoral degree in computer science in 2012 from Vinayaka Missions University, Salem. He received his M. Phil (Computer Science) degree in 2002 from Manonmaniam Sundaranar University, Tirunelveli and MCA from Bharathidhason University, Salem. He is working as Associate Professor at Nesamony Memorial Christian College, Marthandam. His major research interests are Cryptography, Network Security, Segmentation and Classification.