Performance analysis of soft computing techniques for the automatic classification of fruits dataset

Different properties of numerous types of fruits and vegetable classification are still an intricate task. The soft computing strategies are used to recognize a fruit by blending the three basic features which characterize the object: color, shape and texture. The classifiers are relatively effective, when the image feature vector is fused with one another. This technique decreases the dimensionality of the feature vector. So the combined and normalized features of the image are producing better classification accuracy with minimum number of training data. K-nearest neighbor (K-NN), linear discriminant analysis, naive Bayes, error-correcting output classifier and decision tree classifiers are used for image recognition process. A tenfold cross-validation technique is used to improve the classification accuracy of the classifier. The experiment is demonstrated in all the five techniques with 2400 images from the 24 categories of fruits and vegetables. The K-NN scored 97.5% of classification accuracy.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[3]  Yudong Zhang,et al.  Fruit classification by biogeography‐based optimization and feedforward neural network , 2016, Expert Syst. J. Knowl. Eng..

[4]  Hélio Pedrini,et al.  Automatic Fruit and Vegetable Recognition Based on CENTRIST and Color Representation , 2016, CIARP.

[5]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[6]  Guangchun Gao,et al.  Study on Fruit Recognition Methods Based on Compressed Sensing , 2015 .

[7]  Mariusz Kubanek,et al.  Feature Extraction of Palm Vein Patterns Based on Two-Dimensional Density Function , 2015, ICAISC.

[8]  Holger R. Maier,et al.  Data splitting for artificial neural networks using SOM-based stratified sampling , 2010, Neural Networks.

[9]  Tristan Perez,et al.  Visual detection of occluded crop: For automated harvesting , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[10]  K. Umamaheswari,et al.  A bio-inspired swarm intelligence technique for social aware cognitive radio handovers , 2017, Comput. Electr. Eng..

[11]  Leon N. Cooper,et al.  Improving nearest neighbor rule with a simple adaptive distance measure , 2007, Pattern Recognit. Lett..

[12]  K. Etemad,et al.  Discriminant analysis for recognition of human face images , 1997 .

[13]  Sung-Bae Cho,et al.  Fingerprint classification using one-vs-all support vector machines dynamically ordered with naive Bayes classifiers , 2008, Pattern Recognit..

[14]  Anand Singh Jalal,et al.  Apple disease classification using color, texture and shape features from images , 2016, Signal Image Video Process..

[15]  Nikhil R. Pal,et al.  A novel training scheme for multilayered perceptrons to realize proper generalization and incremental learning , 2003, IEEE Trans. Neural Networks.

[16]  Yoram Singer,et al.  Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers , 2000, J. Mach. Learn. Res..

[17]  Derong Liu,et al.  Optimization of electricity consumption in office buildings based on adaptive dynamic programming , 2017, Soft Comput..

[18]  Digvir S. Jayas,et al.  Hyperspectral imaging to classify and monitor quality of agricultural materials , 2015 .

[19]  R. Arulmurugan,et al.  Classification of sentence level sentiment analysis using cloud machine learning techniques , 2017, Cluster Computing.

[20]  Shixiong Xia,et al.  An Improved KNN Text Classification Algorithm Based on Clustering , 2009, J. Comput..

[21]  Konstantinos N. Plataniotis,et al.  Face recognition using LDA-based algorithms , 2003, IEEE Trans. Neural Networks.

[22]  Wei Chu,et al.  Multi-category Classification by Soft-Max Combination of Binary Classifiers , 2003, Multiple Classifier Systems.

[23]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  José de Jesús Rubio,et al.  A method with neural networks for the classification of fruits and vegetables , 2017, Soft Comput..

[25]  Christian Napoli,et al.  Multi-class Nearest Neighbour Classifier for Incomplete Data Handling , 2015, ICAISC.

[26]  Thomas G. Dietterich,et al.  Solving Multiclass Learning Problems via Error-Correcting Output Codes , 1994, J. Artif. Intell. Res..

[27]  Emmanuel Roux,et al.  Linking clinical measurements and kinematic gait patterns of toe-walking using fuzzy decision trees. , 2007, Gait & posture.

[28]  Patrick C. Chen,et al.  Segmentation by texture using a co-occurrence matrix and a split-and-merge algorithm☆ , 1979 .

[29]  K. Umamaheswari,et al.  Supervised machine learning techniques in cognitive radio networks during cooperative spectrum handovers , 2017, Cluster Computing.