Nosema Pathogenic Agent Recognition Based on Geometrical and Texture Features Using Neural Network Classifier

Analysis of the Nosema Cells Identification for Microscopic Images

“…This section discusses in detail the behavior and features of each experiment and it discusses compromise between accuracy and the robustness of the proposed methods was included. Besides, a comparison vs. the most representative publication on this topic (see Table 8 ), with comparison vs. a previous work [ 14 ], authors increased the dataset from 185 to 2000 images and the extracted features number from 9 to 19, and those features for the Nosema cell are related to several aspects of the image cell: geometric shape, statistical characteristics, texture and color features given by GLCM. Two strategies were followed to recognize Nosema; while only one was followed (ANN) in [ 14 ]; the first strategy consists of the use of calculated characteristics by an ANN and an SVM and the second is based on sub-images extracted from treated microscopic images using an implemented CNN and the tools of transfer Learning.…”

“…Two strategies were followed to recognize Nosema; while only one was followed (ANN) in [ 14 ]; the first strategy consists of the use of calculated characteristics by an ANN and an SVM and the second is based on sub-images extracted from treated microscopic images using an implemented CNN and the tools of transfer Learning. ANN used in [ 14 ] gave a success rate of 91.1% in Nosema recognition. SVM also was used in [ 13 ] to classify the two types of Nosema and other objects.…”

“…They are also the most significant for us because, after several experiments, the best results were achieved using them. These parameters were used and defined in [ 14 ] respectively: The size/the perimeter: given that the shape of the Nosema cell is similar to an ellipse form and the other objects have different rounds shapes, perimeter formula of an ellipse adopted have been adopted in this study. This calculation is based on a and b variables where a is the semi-major axis and b is the semi-minor axis.…”

“…They are also the most significant for us because, after several experiments, the best results were achieved using them. These parameters were used and defined in [14] respectively:…”

“…A segmentation technique and a support vector machine algorithm were then applied to microscopic processed images to automatically classify N. apis and N. ceranae microsporidia. In [ 14 ], the authors used the image processing techniques to extract the most valuable features from Nosema microscopic images and apply an Artificial Neural Network (ANN) for the recognition, which was statistically evaluated using the cross-validation technique. The last two works used image processing tools for feature extraction and Support Vector Machine (SVM) and ANN for classification.…”