Automated Wheat Disease Classification Under Controlled and Uncontrolled Image Acquisition

Abstract

This paper presents a practical classification system for recognising diseased wheat leaves and consists of a number of components. Pre-processing is performed to adjust the orientation of the primary leaf in the image using a Fourier Transform. A Wavelet Transform is then applied to partially remove low frequency information or background in the image. Subsequently, the diseased regions of the primary leaf are segmented out as blobs using Otsu's thresholding. The disease blobs are normalised and then radially partitioned into sub-regions (using a Radial Pyramid) representing radial development of many diseases. Finally, global features are computed for different pyramid layers and combined to create a feature descriptor for training a linear SVM classifier. The system is evaluated by classifying three types of wheat leaf disease: nondiseased, Yellow Rust and Septoria. The classification accuracies are slightly over 95% and 79% for images captured under controlled and uncontrolled conditions, respectively.

A Lightweight Mobile System for Crop Disease Diagnosis

“…Pre-processing requires user participation only when the user needs to upload an image. Previous research [9] has demonstrated the potential for using a 2-D Discrete Fourier transform (DFT) in detecting global frequency where wheat leaf veins are strongly aligned in a particular direction (corresponding to the orientation of the leaf edge itself). The resulting Fourier spectrum represents a spectrum line that is orthogonal to the leaf orientation.…”

“…Disease segmentation is required to extract the disease areas from the main leaf. Otsu thresholding is applied to and colour components of the leaf image, as it has been shown in previous work that these combined colour components for disease segmentation are robust to different lighting conditions [9]. Then the contours of individual disease patches are extracted based on border following algorithms to find connected components of a binary disease image [12].…”

Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment

“…To segment the disease region, Otsu's binary thresholding is applied on the Cb and Cr colour components (of the YCbCr colour model) which are shown to be robust to different lighting condition [12]. Figure 3 illustrates segmented disease samples of three types of wheat leaves, where the individual disease patch (spot) is computed for 15 different shape features.…”