scispace - formally typeset
Search or ask a question
Patent

Scab segmentation method in crop disease blade image

TL;DR: In this paper, a scab segmentation method in a crop disease blade image is presented. But the method is not suitable for field operation, and it cannot be applied to the mobile terminal such as a smart phone.
Abstract: The present invention provides a scab segmentation method in a crop disease blade image. The method comprises the following steps: obtaining a color image including crop disease blades from an image collection device, performing normalization processing, converting the color image to a CIEL*a*b* color space, setting the initial classification number as 2, employing the adaptive feature learning method to learn the scab in the image and the values of the initial classification color features R, G and B of the background blades, calculating the distance from each pixel point to a classification center, and performing data classification; and calculating the distance between a* mean values, and stopping the segmentation if the distance of the a* value obtains the maximum result. The method overcomes the problems that different crops and different scab segmentation results are unstable in the prior art, improves the segmentation precision and the adaptation of the scab segmentation algorithm, can be applied to the mobile terminal such as a smart phone and the like, is suitable for field operation, and widen the application range.
Citations
More filters
Patent
18 May 2018
TL;DR: In this paper, a highvoltage cabinet switch automatic recognition method based on a convolutional neural network was proposed, which comprises the steps that (1) a to-be-recognized switch cabinet image is read, and a scaled input image is acquired; (2) multiple prior boxes are acquired through clustering according to true box data of training samples; (3) the CNN is constructed and trained according to prior box data.
Abstract: The invention relates to a high-voltage cabinet switch automatic recognition method based on a convolutional neural network The method comprises the steps that (1) a to-be-recognized switch cabinet image is read, and a scaled input image is acquired; (2) multiple prior boxes are acquired through clustering according to true box data of training samples; (3) the convolutional neural network is constructed and trained according to prior box data; (4) the scaled input image is used as input of the trained convolutional neural network, and a recognition position and category information of a switch target are obtained; (5) a non-maximum suppression method is adopted to process the recognition position and the category information of the switch target, and a final prediction box is obtained; and (6) prediction box data is mapped to the to-be-recognized switch cabinet image, the prediction box is drawn in the to-be-recognized switch cabinet image, and a category tag of the target is markedCompared with the prior art, the method has the advantages of high robustness and generalization, fast convergence, accurate selection and the like

8 citations

Patent
19 Feb 2019
TL;DR: In this paper, the least square circle error value of the connected component in the cotton lesion region image was calculated to obtain the segmentation result of the adherent lesion image.
Abstract: The embodiment of the invention provides a cotton leaf adhesion lesion spot image segmentation method and system. The method comprises the following steps: S1, obtaining the least square circle errorvalue of the connected component in the cotton lesion region image; S2, adjusting the h-threshold of the H-minima method based on the least square circle error value., and comparing the cotton lesionregion images converted by H-minima method with h-threshold until the number of minimum points changes, then carrying out distance transformation and watershed segmentation; 3, judging whether that error value of the least square circle before the watershed division is great than the error value of the least square circle after the watershed division; If not, the segmentation is finished to obtaina lesion segmentation area; S4, marking the lesion segmentation region, and performing logical operation on the lesion segmentation region and the original cotton lesion image to obtain the segmentation result of the adherent lesion image. The method and system can realize the extraction of cotton lesion area and the automatic segmentation of adherent lesion, which is of great significance to thediagnosis of cotton diseases.

1 citations

Patent
03 Aug 2018
TL;DR: In this article, a vegetable leaf disease image segmentation method and system and a computer readable storage medium are presented, which includes the following steps that 1, superpixel clustering processing is conducted on vegetable leaf images to obtain superpixel segmentation images; 2, significance region detection processing is performed on the superpixel segments to obtain lesion significance images; 3, the lesions significance images are processed to obtain non-lesion pixel sets; 4, region growing an region merging are conducted on pixel points in the non-leion pixels sets to get lesion areas and normal
Abstract: The invention discloses a vegetable leaf disease image segmentation method and system and a computer readable storage medium. The vegetable leaf disease image segmentation method includes the following steps that 1, superpixel clustering processing is conducted on vegetable leaf images to obtain superpixel segmentation images; 2, significance region detection processing is conducted on the superpixel segmentation images to obtain lesion significance images; 3, the lesion significance images are processed to obtain non-lesion pixel sets; 4, region growing an region merging are conducted on pixel points in the non-lesion pixel sets to obtain lesion areas and normal areas of the vegetable leaf images. By the adoption of the vegetable leaf disease image segmentation method and system and the computer readable storage medium, leaf diseases in greenhouses can be rapidly and effectively detected and extracted under the conditions that no chemical reagents are in use and diseased vegetable leaves are not damaged, and therefore the vegetable leaf disease image segmentation method and system and the computer readable storage medium can be well applied in monitoring greenhouse vegetable diseases.
Patent
30 Nov 2018
TL;DR: In this paper, a method for automatically extracting and quantifying the color of a lesion area of an infantile hemangioma was proposed, which comprises the steps of extracting the lesion part in an image of the infantile haemaglioma and marking the remaining part as a skin area; converting color space of the lesions area and the skin area from red green blue (RGB) to international commission on illumination (CIE) lab; extracting a mean value of chromatic values of three channels of the skin areas to obtain a mean vector of the chrom
Abstract: The invention discloses a method for automatically extracting and quantifying the color of a lesion area of an infantile hemangioma. The method comprises the steps of extracting a lesion part in an image of the infantile hemangioma, marking the lesion part as the lesion area and marking the remaining part as a skin area; converting color space of the lesion area and the skin area from red green blue (RGB) to international commission on illumination (CIE) Lab; extracting a mean value of chromatic values of three channels of the skin area to obtain a mean vector of the chromatic value of the skin area; extracting the mean value of chromatic values of three color channels of the lesion area to obtain the mean vector of the chromatic value of the lesion area; calculating distance by utilizingthe mean vector of the chromatic value of the skin area and the mean vector of the chromatic value of the lesion region, wherein the distance comprises Euclidean distance, Manhattan distance, Chebyshev distance, included angle cosine distance and related distance; and inputting the distance into an SVM (Support Vector Machine) classification model and outputting a classification result to realizeautomatic quantification of the color of the lesion area of the infantile hemangioma. Through the method disclosed by the invention, the automatic extraction and quantification of the color of the lesion area of the infantile hemangioma are realized.
Patent
22 Jun 2018
TL;DR: Zhang et al. as mentioned in this paper provided a crop leaf image enhancement method and device, which comprises the following steps: Zooming on a collected color image, and obtaining crop leaf color images; S2) carrying out filtering processing on the crop leaf colour images based on an improved bootstrap filtering algorithm to obtain a first color image; S3) subtracting the first colour image from the crop leaves color images, wherein the second color image is a detailed image of the first one, and S4) based on the mean value of pixel brightness values in thesecond color image and
Abstract: The invention provides a crop leaf image enhancement method and device. The method comprises the following steps: S1) carrying out zooming on a collected color image, and obtaining crop leaf color images; S2) carrying out filtering processing on the crop leaf color images based on an improved bootstrap filtering algorithm to obtain a first color image; S3) subtracting the first color image from the crop leaf color images to obtain a second color image, wherein the second color image is a detailed image of the first color image; and S4) based on the mean value of pixel brightness values in thesecond color image and contrast ratio of each pixel of the second color image, fusing the first color image and the second color image to obtain a crop leaf enhanced image. The method and device realize enhancement of the crop leaf image, thereby reducing noise influence, highlighting useful information in the image and improving image quality; and the method and device overcome the problems of color distortion and not obvious enhancement effect and the like in the prior art.
References
More filters
01 Jan 2012
TL;DR: A comparison of the effect of CIELAB, HSI and YCbCr color space in the process of disease spot detection is done and threshold can be calculated by applying Otsu method on color component to detect the disease spot.
Abstract: In this research, an algorithm for disease spot segmentation using image processing techniques in plant leaf is implemented. This is the first and important phase for automatic detection and classification of plant diseases. Disease spots are different in color but not in intensity, in comparison with plant leaf color. So we color transform of RGB image can be used for better segmentation of disease spots. In this paper a comparison of the effect of CIELAB, HSI and YCbCr color space in the process of disease spot detection is done. Median filter is used for image smoothing. Finally threshold can be calculated by applying Otsu method on color component to detect the disease spot. An algorithm which is independent of background noise, plant type and disease spot color was developed and experiments were carried out on different "Monocot" and "Dicot" family plant leaves with both, noise free (white) and noisy background.

164 citations

01 Jan 2013
TL;DR: Various methods used to study of leaf disease detection using image processing are provided for increasing throughput and reduction subjectiveness arising from human experts in detecting the leaf disease.
Abstract: In agriculture research of automatic leaf disease detection is essential research topic as it may prove benefits in monitoring large fields of crops, and thus automatically detect symptoms of disease as soon as they appear on plant leaves The term disease is usually used only for destruction of live plants This paper provides various methods used to study of leaf disease detection using image processing The methods studies are for increasing throughput and reduction subjectiveness arising from human experts in detecting the leaf disease(1)digital image processing is a technique used for enhancement of the image To improve agricultural products automatic detection of symptoms is beneficial

70 citations

Patent
06 May 2015
TL;DR: In this article, the saliency of each pixel point according to a multi-scale neighborhood was calculated to obtain a final salient image, and then the final image was cut into K areas by the K means clustering method, and the area of which the average value of the salience of the pixel points is more than a set threshold was extracted as a salient area.
Abstract: The invention discloses a method for recognizing diseases of crop leaves. The method comprises the steps of converting acquired images into CIELab colored space images; calculating the saliency of each pixel point according to a multi-scale neighborhood to obtain a final salient image; cutting the final salient image into K areas by the K means clustering method; extracting the area of which the average value of the saliency of the pixel points is more than a set threshold as a salient area; adjusting the extracted salient area to obtain a scab image; extracting the color and local texture feature parameters of the scab image; inputting the obtained color and local texture feature parameters into the neural network for recognizing and classifying the diseases. With the adoption of the method, the extracted scab image is free of color distortion, and the diseases recognition accuracy is high.

14 citations

Patent
10 Aug 2016
TL;DR: In this article, a cucumber disease identification method and apparatus based on image information was presented, which is related to the fields of system engineering and information technology and improves the accuracy of identification, and avoids subjectivity and limitation due to artificial identification.
Abstract: The invention discloses a cucumber disease identification method and apparatus based on image information, and relates to the fields of system engineering and information technology. The invention acquires a leaf disease image of a cucumber to be identified; carries out image segmentation for the leaf disease image to obtain segmented leaf patches; extracts features of the leaf patches to obtain disease feature information; carries out disease identification for the disease feature information according to a preset disease feature sample, to obtain the disease of the cucumber to be identified; and therefore, improves the accuracy of identification, and avoids subjectivity and limitation due to artificial identification.

14 citations

Patent
16 Nov 2016
TL;DR: In this article, a water-shed algorithm was used to segment the luminance component gradient map, and then the hue and saturation components of the segmented image to obtain two segmented images.
Abstract: The invention provides a segmentation method and device of protected vegetable clear-edge leaf surface disease spots. The method comprises the following steps: after the non-green background of an image to be processed is removed, according to an HIS (Hue, Saturation or Intensity) color model, obtaining the luminance component gradient map after the image is processed; utilizing a water-shed algorithm to segment the luminance component gradient map, and then, segmenting the hue and saturation components of the segmented image to obtain two segmented images; according to a preset rule, independently combining and extracting the segmentation blocks of the three segmented images to obtain three target leaf areas to be selected; according to the obtained target leaf areas to be selected and the pixel number of the circumscribed minimum convex polygon of the target leaf areas to be selected, calculating three leaf integrity parameters, selecting an area corresponding to a maximum value as a target leaf area, and obtaining the gray level image of an image to be processed and the gray level value of each pixel in the target leaf area in the gray level image; and according to the gray level value, classifying all pixels of the target leaf area into multiple classes, and obtaining the disease spot areas of the target leaf area according to the classes. By use of the method, the disease spot areas of the leaf can be segmented through a computer vision technology.

2 citations