Analysis of visual features and classifiers for Fruit classification problem

Computer Science

• Classifier 100%
• Classification Problem 100%
• Visual Feature 100%
• Machine Learning Technique 66%
• Deep Neural Network 66%
• Classification Accuracy 66%
• Scale-Invariant Feature Transform 66%
• back-propagation neural network 66%
• Linear Discriminant Analysis 33%
• classification result 33%
• Texture Feature 33%
• Decision Trees 33%
• Wavelet Transforms 33%
• Support Vector Machine 33%
• Nave Bayes 33%
• Training Dataset 33%
• k-Nearest Neighbors Algorithm 33%
• Visual Inspection 33%
• color feature 33%
• Support Vector Machine 33%
• Illumination Effect 33%

Engineering

• Classification Problem 100%
• Deep Neural Network 66%
• Machine Learning Technique 66%
• Backpropagation 66%
• Classification Accuracy 66%
• Similarities 33%
• Feedforward 33%
• Nearest Neighbor 33%
• Good Result 33%
• Support Vector Machine 33%
• Visual Inspection 33%
• Texture Feature 33%
• Decision Analysis 33%

Biochemistry, Genetics and Molecular Biology

• Back Propagation 100%
• Illumination 50%
• Support Vector Machine 50%
• Decision Trees 50%
• K Nearest Neighbor 50%
• Supervised Machine Learning 50%