Machine Learning Algorithms and Applications. Группа авторов

eggs and unhatched eggs. The positive samples consist of images where an individual egg is visible completely, while the negative samples consist of eggs that are partially visible and have multiple egg entries. Figure 2.5 represents the classifier model that is trained to determine positive and negative samples, and the positive samples are later trained to predict the egg center location in terms of pixel values. Further, during the practical application, the center location of the egg predicted is used to crop a single egg data to be fed into a classifier that determines the class of the selected egg into HC or UHC. Figure 2.6 represents an overall result of locating egg centers using egg location predictor CNN model for one of the test data sheets where all egg centers are marked with a blue dot. A sliding window of (32 × 32) with a stride of (4, 4) was used to achieve the results.

      2.3.4 Predicting Egg Class

The sliding window method is used to generate input images, and a single egg may be represented by many image windows each of size 32 × 32. Euclidean distance equation, , was used to select the egg center by combining all the egg location predictions that fall within a certain user-defined distance limit. (x1, y1) and (x2, y2) are the reference pixel and pixel under consideration. Since the egg diameter is well within the range of 28 to 32 pixels, a distance limit is set that is equal to the radius of the egg, i.e., 16 pixels. Any center locations that fall within this limit are considered to be representing same egg and hence combined to generate single egg location that can be then cropped by using Equations (2.4) to (2.7), where (xa, ya) are the resulting egg location after averaging all predicted egg locations that fall within distance limits. (x, y) pixel is the original location while w, h represents the width and height of the image to be cropped that is equal to 32 pixels. The resulting images are fed into the egg class predictor CNN model, which provides categorical data to distinguish the input image into class HC or UHC. The specification of the egg class predictor CNN model is represented in Table 2.3.

(2.4)

      (2.5)

      (2.6)

(2.7)

Table 2.2 Specifications of egg location CNN model.

Input image	Activation/output	Training samples	Test samples	Validation samples	Test loss	Validation loss
32 × 32	Regression Center of the egg (x, y)	439 × 10^3	51.6 × 10^3	25.8 × 10^3	0.5488	0.5450

Figure 2.5 CNN training model to predict egg location in terms of pixel values.

Figure 2.6 Result of egg location CNN model.

Table 2.3 Specification of egg class predicator CNN model.

Input image	Activation/output	Training samples	Test samples	Validation samples	Test loss	Accuracy on the test set	Accuracy on the validation set
32 × 32	SoftMax 2 class-(0/1)	2.4 × 10^6	80.2 × 10^3	30 × 10^3	0.0077	99.8115%	99.7981%

The overall result of egg classification and counting yields an accuracy greater than 97%, and Figure 2.7 represents the result generated using the proposed method where green dots represent the hatched eggs while red dots represent unhatched eggs. Some of the areas of the images are zoomed and shown separately in Figure 2.7 since the input image is too big to fit in the page and eggs are minuscule to see any features.

Figure 2.7 Result of egg classification generated by the proposed method.

2.4 Dataset Generation

      In comparison with the conventional method of extracting egg count information using digital images that hardly require any training data, the proposed method that employs the CNN technique required large datasets to learn the features automatically to provide the required results. The CNN method uses plenty of training data along with test and validation datasets as the number of hidden layers increases.

      There are many datasets available for free that can be downloaded to train our own CNN models to classify handwritten digits, identify objects, and many more. But there is no single public dataset available corresponding with the sericulture field especially silkworm egg counting or classification. So, in our work, training datasets were generated by cropping class images from the silkworm egg sheet and providing class