The world population, and thus the need for food, is increasing every day. This leads to the ultimate question of how to increase food production with limited time and scarce land. Another obstacle to meet the food demand includes the stresses a plant goes through. These may be abiotic or biotic, but the majority are biotic, i.e., plant diseases. The major challenge is to mitigate plant diseases efficiently, more quickly and with less manpower. Recently, artificial intelligence has turned to new frontiers in smart agricultural science. One novel approach in plant science is to detect and diagnose plant disease through deep learning and hyperspectral imaging. This smart technique is very advantageous for monitoring large acres of field where the availability of manpower is a major drawback. Early identification of plant diseases can be achieved through machine learning approaches. Advanced machine learning not only detects diseases but also helps to discover gene regulatory networks and select the genomic sequence to develop resistance in crop species and to mark pathogen effectors. In this review, new advancements in plant science through machine learning approaches have been discussed.

Image segmentation is a typical operation in many image analysis and computer vision applications. However, hyperspectral image segmentation is a field which have not been fully investigated. In this study an analogue- digital image segmentation technique is presented. The system uses an acousto-optic tuneable filter, and a CCD camera to capture hyperspectral images that are stored in a digital grey scale format. The data set was built considering several objects with remarkable differences in the reflectance and brightness components. In addition, the work presents a semi-supervised segmentation technique to deal with the complex problem of hyperspectral image segmentation, with its corresponding quantitative and qualitative evaluation. Particularly, the developed acousto-optic system is capable to acquire 120 frames through the whole visible light spectrum. Moreover, the analysis of the spectral images of a given object enables its segmentation using a simple subtraction operation. Experimental results showed that it is possible to segment any region of interest with a good performance rate by using the proposed analogue-digital segmentation technique.

This paper takes a look at the state-of-the-art solutions in the field of spectral imaging systems by way of application examples. It is based on a comparison of currently used systems and the challenges they face, especially in the field of high-altitude imaging and satellite imaging, are discussed. Based on our own experience, an example of hyperspectral data processing is presented. The article also discusses how modern algorithms can help in understanding the data that such images can provide.