A Machine Vision System for Quality Inspection of Pine Nuts
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 9
Abstract
Computers and artificial intelligence have penetrated in the food industry since last decade, for intellectual automatic processing and packaging in general, and in assisting for quality inspection of the food itself in particular. The food quality assessment task becomes more challenging when it is about harmless internal examination of the ingredient, and even more when its size is also minute. In this article, a method for automatic detection, extraction and classification of raw food item is presented using x-ray image data of pine nuts. Image processing techniques are employed in developing an efficient method for automatic detection and then extraction of individual ingredient, from the source x-ray image which comprises bunch of nuts in a single frame. For data representation, statistical texture analysis is carried out and attributes are calculated from each of the sample image on the global level as features. In addition co-occurrence matrices are computed from images with four different offsets, and hence more features are extracted by using them. To find fewer meaningful characteristics, all the calculated features are organized in several combinations and then tested. Seventy percent of image data is used for training and 15% each for cross-validation and test purposes. Binary classification is performed using two state-of-the-art non-linear classifiers: Artificial Neural Network (ANN) and Support Vector Machines (SVM). Performance is evaluated in terms of classification accuracy, specificity and sensitivity. ANN classifier showed 87.6% accuracy with correct recognition rate of healthy nuts and unhealthy nuts as 94% and 62% respectively. SVM classifier produced the similar accuracy achieving 86.3% specificity and 89.2% sensitivity rate. The results obtained are unique itself in terms of ingredient and promising relatively. It is also found that feature set size can be reduced up to 57% by compromising 3.5% accuracy, in combination with any of the tested classifiers.
Authors and Affiliations
Ikramullah Khosa, Eros Pasero
Keywords
Related Articles
- EP ID EP96385
- DOI 10.14569/IJACSA.2016.070937
- Views 74
- Downloads 0
User based Recommender Systems using Implicative Rating Measure
This paper proposes the implicative rating measure developed on the typicality measure. The paper also proposes a new recommendation model presenting the top N items to the active users. The proposed model is based on th...
An Analysis of Brand Selection
It is often observed that consumers select upper class brand when they buy next time. Suppose that former buying data and current buying data are gathered. Also suppose that upper brand is located upper in the variable a...
Speculating on Speculative Execution
Threat actors continue to design exploits that specifically target physical weaknesses in processor hardware rather than more traditional software vulnerabilities. The now infamous attacks, Spector and Meltdown, ushered...
Hybrid Algorithm for the Optimization of Training Convolutional Neural Network
The training optimization processes and efficient fast classification are vital elements in the development of a convolution neural network (CNN). Although stochastic gradient descend (SGD) is a Prevalence algorithm used...
Web Service Architecture for a Meta Search Engine
With the rapid advancements in Information Technology, Information Retrieval on Internet is gaining its importance day by day. Nowadays there are millions of Websites and billions of homepages available on the Internet....