Plant recognition, detection, and counting with deep learning

In agricultural and farm management, plant recognition, plant detection, and plant counting systems are crucial. We can apply these tasks to several applications, for example, plant disease detection, weed detection, fruit harvest system, and plant species identification. Plants can be identified by looking at their most discriminating parts, such as a leaf, fruit, flower, bark, and the overall plant, by considering attributes as shape, size, or color. However, the identification of plant species from field observation can be complicated, time-consuming, and requires specialized expertise. Computer vision and machine-learning techniques have become ubiquitous and are invaluable to overcome problems with plant recognition in research. Although these techniques have been of great help, image-based plant recognition is still a challenge.  There are several obstacles, such as considerable species diversity, intra-class dissimilarity, inter-class similarity, and blurred resource images. Recently, the emerging of deep learning has brought substantial advances in image classification. Deep learning architectures can learn from images and notably increase their predictive accuracy. This thesis provides various techniques, including data augmentation and classification schemes, to improve plant recognition, plant detection, and plant counting system.

Dissertation: http://hdl.handle.net/11370/ed1f333e-4203-4a28-8947-39acc4bb1e0a