CNN based approach for identifying banana species from fruits
- PDF / 1,193,152 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 47 Downloads / 230 Views
ORIGINAL RESEARCH
CNN based approach for identifying banana species from fruits M. Vijayalakshmi1
•
V. Joseph Peter2
Received: 25 September 2019 / Accepted: 6 November 2020 Ó Bharati Vidyapeeth’s Institute of Computer Applications and Management 2020
Abstract Classification and recognition of fruits are still the challenging one as there are different classes of fruit types having wide inter-class resemblance. This paper proposes a banana identification model using a five-layer convolution neural network (CNN) which composed of convolution layer, pooling layer and fully connected layer. Fruits like Apple, Strawberry, and Orange, Mango and banana have been analyzed and several features have been extracted using deep learning-based CNN algorithm. Finally, the fruit identification process is done by random forest and K-Nearest Neighborhood (K-NN) classifying algorithms. A regular digital camera is used for the image acquisition process. All image manipulation processes are performed in MATLAB-17 environment.Experiments are conducted in our database consisting of 5887 fruit images. The performance of the proposed deep learning basedrandom forest and KNN classifiers are compared with the existing feature extraction method of HOG based random forest and KNN in terms of accuracy, precision, recall and f-score and we have achieved a accuracy rate of 96.98% for deep feature-random forest classification combination algorithm which is better than the deep feature-KNN, HOG based KNN and random forest classifiers.
& M. Vijayalakshmi [email protected] V. Joseph Peter [email protected] 1
Manonmaniam Sundaranar University, Tirunelveli, Tamilnadu, India
2
Research Department of Computer Science, Kamaraj College, Thoothukudi, Tamilnadu, India
Keywords Convolution neural network Deep learning Fruit classification KNN Random forest Abbreviations ANN Artificial neural network CNN Convolution neural network KNN K-nearest neighborhood
1 Introduction Before developing algorithms for identifying maturity level of banana, it would be fruitful to develop an automated process for identifying the banana fruit from images containing multiple fruit varieties like apple, orange, strawberry etc. The utilization of computerizes system is extremely normal in horticulture and industries as natural product gathering robot [1], products arranging machine, and product scanner in grocery stores. These are used to replace the manual involvement by machines. Towards improvement in this area an algorithm for identifying the banana fruit from the fruit images is proposed here. Feature detection is a low level image processing operation where it is usually performed as the first operation on an image. A feature can be defined as the ‘‘interest’’ part of an image [2]. The features color, shape, texture and intensity were regularly utilized for acknowledging the organic products. A few methodologies concentrate on explicit element like shading while remaining centers around consolidating at least two highlights, bringing about a few
Data Loading...
