Deep learning has shown to achieve dramatic results in image classification tasks. However, deep learning models require large amounts of data to train. Most of the real-world datasets, generally insect classification data does not have large number of training dataset. These images have a large amount of noise and various differences. The paper proposes a novel architectural model which removes the background noise and classify the Tiger beetles. Here object location is identified using contours by converting the original coloured image to white on black background. Then the remaining background is eliminated using grabcut algorithm. Later the extracted images are classified using a modified SqueezeNet transfer learning model to identify the tiger beetle class up to genus level. Transfer learning models with fewer trainable parameters performed well than the total number of parameters in the original model. When evaluating results it was identified that by freezing uppermost layers of SqueezeNet model better accuracy can be gained while freezing lowermost layers will reduce the validation accuracy. The proposed model achieved more than 90% for the test set in 40 epochs using 701,481 trainable parameters by freezing the top 19 layers of the original model. Improving the pre-processing to localize insect has improved the accuracy.

深度学习已显示在图像分类任务中取得了惊人的成果。但是，深度学习模型需要大量的数据进行训练。大多数真实世界的数据集，通常昆虫分类数据没有大量的训练数据集。这些图像具有大量的噪点和各种差异。本文提出了一种新颖的建筑模型，该模型可以消除背景噪音并对虎甲虫进行分类。在这里，通过将原始彩色图像转换为黑色背景上的白色，可以使用轮廓识别对象位置。然后，使用抓取算法消除剩余的背景。后来，使用改进的SqueezeNet转移学习模型对提取的图像进行分类，以识别直至甲虫级别的甲虫类。与原始模型中的参数总数相比，具有较少可训练参数的转移学习模型表现良好。在评估结果时，可以确定通过冻结SqueezeNet模型的最上层可以获得更好的精度，而冻结最下层则会降低验证精度。通过冻结原始模型的前19个层，使用701,481个可训练参数，建议的模型在40个时期内的测试集达到了90％以上。改进定位昆虫的预处理可以提高准确性。通过冻结原始模型的前19个层，使用701,481个可训练参数，建议的模型在40个时期内的测试集达到了90％以上。改进定位昆虫的预处理可以提高准确性。通过冻结原始模型的前19个层，使用701,481个可训练参数，建议的模型在40个时期内的测试集达到了90％以上。改进定位昆虫的预处理可以提高准确性。