Tuesday, July 5, 2016

Classification of Grain Based On the Morphology, Color and Texture Information Extracted From Digital Images

Brazil is one of the largest grain producers in the world and grain classification are of great importance to the industry, since they are related to quality and economic factors. The objective of this study was to use methods of data analysis of shape, color and  texture extracted from  digital images for grain classification. From the results obtained it was demonstrated that  the  use of  patterns of  morphology, color  and  texture  extracted from images using  the  digital imaging processing techniques are effective for grain classification. The LBP texture pattern proved the most efficient information among the three, and with it alone was possible to reach a 94% hit rate. Combining addition to the pattern shape of LBP information with FCC and color with HSV was possible to improve the success rate to 96%.

[+] Read full-text

USING PYTHON WITH SIMPLECV TO DETECT A CORN KERNEL IN DIGITAL IMAGE

Corn  kernels  can  have  their  nutritional  and  economic  value  hindered  by factors such as breakage and rot on the grain. The grain classification, in general, is made  by  visual  inspection  of  licensed  professionals,  and  is  a  tedious  and  tiresome process. Besides, the possibility of error is large, due to visual human subjectivity. In an attempt to reduce this subjectivity by using image processing techniques, this paper presents a computational  method  for  acquiring, preprocessing, and segmentation of corn  kernels  of  digital  images. It  is  expected  that,  with  the  proposed  program, researchers  can  have  either  their  focus  or  their  efforts  on  feature  extraction, recognition and interpretation of grains under analysis without spend time with steps related to image manipulation issues.

[+] Read full-text

Saturday, August 8, 2015

Metadata Extraction for Calculating Object Perimeter in Images

The objective of this paper is to present the results of a class developed with routines in Java language, and contribution of OpenCV library, for analysis and extraction of metadata from images. To evaluate the developed class, three different figures were produced in cardstock and their perimeters were measured with a millimeter ruler. Then these figures were scanned for further image analysis with aid of the developed class. The images of the figures were initially saved in BMP format. After it, each of the images in BMP format were saved in JPG and PNG file formats resulting, at the end, on nine images. The validation of the correct extraction of the image metadata and so the perimeter value of the object was performed by comparing the values obtained by direct measurement perimeter of the figure, with a millimeter ruler, and the values obtained with digital image processing, counting the contour pixels of the image of the figure, and using the image resolution, one of the extracted metadata. For the edge detection and counting of the contour pixels of object, the algorithms cvFindContours() and cvContourPerimeter(), of OpenCV library, were used. It was obtained, for the worst case, a percentage error of 8.0 %, for images with BMP and PNG format. Therefore, the developed class presents satisfactory results and is recommended to extract and calculate measures of an object present in the image.  [+] Full Paper

Monday, July 13, 2015

Using SimpleCV for seed metadata extraction

Computing approaches have been used in agriculture problems. Seeds information like shape, size, texture. color, etc are important for agriculture traits resulting in quality and market price. The purpose of this work was used digital image processing with metadata techniques to generate data from seeds using SimpleCV framework and programming language Python... [+] Read more