PB3C-CNN: An integrated Parallel Big Bang-Big Crunch and CNN based approach for plant leaf classification

Plant identification and classification are critical to understand, protect, and conserve biodiversity. Traditional plant classification requires years of intensive training and experience, making it difficult for others to classify plants. Plant leaf classification is a challenging issue as similar features appear in different plant species. With the development of automated image-based classification, machine learning (ML) is becoming very popular. Deep learning (DL) methods have significantly improved plant image identification and classification. In the last decade, convolutional neural networks (CNN) have entirely dominated the field of computer vision, showing outstanding feature extraction capabilities and significant identification and classification performance. The capability of CNN lies in its network. The primary strategy to continue this trend in the literature relies on further scaling networks in size. However due to increase in network size, costs increase rapidly, while performance improvements may be marginal. Hence, there is a need to optimize the CNN network to get the desired result with optimal size of machine learning model. This paper proposes a parallel big bang-big crunch (PB3C) based approach to automatically evolve the architecture of CNN. The proposed approach is validated on plant leaf classification application and compared with other existing machine learning-based approaches. From the comparision results we observed that the obtained it was found that the proposed approach was able to outperforms all the 11 existing state-of-the-art techniques.