AUTOMATIC CONTEXTUAL CROPPING AND …

1 International Journal of Scientific Research engineering & Technology (IJSRET), ISSN 2278 0882. Volume 4, Issue 3, March 2015. 223. AUTOMATIC CONTEXTUAL CROPPING AND FEATURE. EXTRACTION FOR PLANT LEAF RECOGNITION. VIJAYALAKSHMI B 1 V. MOHAN 2. 1 2. Assistant Professor ( ), Department of MCA, Professor and Head of Department, K. L. N. College of engineering , Department of Mathematics, Sivagangai District, TamilNadu, India Thiagarajar College of engineering , Madurai, TamilNadu, India report describes our approach for AUTOMATIC CROPPING ABSTRACT and extracting basic geometric features. The Plants are the mainstay of all life on Earth and an arrangement of the report is as follows: section2 outlines important resource for human welfare.

2 Plant the need for AUTOMATIC image CROPPING , section 3, identification is really significant in agriculture for the describe the proposed method with algorithm steps, management of plant or plant cases. This paper section 4, gives Experimental Result and discussions, presents a simple and computationally efficient and section 5 brings up the overall conclusion and scope method to plant identification using digital image for future inquiry. processing. The proposed approach consists of three phases: find out the four points, crop the image by 2. NEED FOR IMAGING CONTEXTUAL . using four points, and calculate some basic geometric CROPPING .

3 Features. CROPPING simply refers to eliminating unwanted portions Keywords: Plant Identification, CROPPING , feature of an image. It can as well be utilized to produce an extraction, Euclidean distance. image of a specific size or dimension Thither are many reasons to crop an image; for 1. INTRODUCTION instance, Fitting an image to fill a form, Plants are necessary to the balance of natural Getting rid of a part of the background to surroundings and in people's lives. They are the ultimate highlight the issue, and so on source of food and metabolic energy for closely all animals, which cannot make their own food.

4 Thus the In leaf identification system, the user has used mobile study of plants is vital because they are an essential part phone, digital camera or notepad to acquire the leaf. of life on Earth. A digital plant identification system can When they put-on the leaf, distance from acquiring the be used for fast characterization of plant species without instruments to the leaf are problematic. [1] This distance needing the knowledge of botanists, thus atomizing their may be small or far. Suppose the distance is far from the work. object, there is useless space around the object(s) of In order to extract any specific information, image interest.

5 It will increase the computation time also. preprocessing steps are carried out before the actual To avoid such problem many tools are available to analysis of the image data. Preprocessing refers to the crop contextually down to the minimum dimensions that initial processing of input leaf image to remove the noise still impart the substance or context of your icon. and accurate the distorted or degraded data. Even though many tools are available, we will Preprocessing techniques like grayscale conversion, conform to any one of the way in manually. Smoothing, resize, filtering and CROPPING . Many times i) Mention the parameter (x1, y1) as starting digital images shot for Web use have a border of useless passion of rectangle and (x2, y2) as an end space around the object(s) of interest.

6 Rather than crop Position of the rectangle. to precisely the film or chip's border, crop contextually ii) Click on the upper left hand corner of the area down to the minimum dimensions that still impart the you wish to keep. While controlling the mouse substance or context of your icon. button, drag toward the bottom right of the CROPPING simply mentions to removing unwanted picture. components of an icon. It can as well be utilized to Then, measuring physiological Width and the diameter produce an image of a specific size or dimension. This is the basic Geometric features in feature extraction of International Journal of Scientific Research engineering & Technology (IJSRET), ISSN 2278 0882.

7 Volume 4, Issue 3, March 2015. 224. leaf shape A human must click the two Steps to the first function: terminals of the main vein of the leaf via mouse click 1. Take the image and threshold value. [2] [3] [4]. This problem also happens with methods, 2. Initialize leftx= 0 (zero) and lefty= 0. extracting features in the plant leaf recognition system (null), rightx=0 and righty = 0. Previous works have some disadvantages. To overcome 3. Start raster scanning (column wise) of the image manual interaction in the leaf identification system, matrix from the protruding location. hence this paper proposes the AUTOMATIC CONTEXTUAL i.

8 For i=2: n-1. CROPPING . ii. For j = 2: m-1. 4. Determine for each pixel value of an image 3. PROPOSED METHODOLOGY having greater than threshold value or lessthen the threshold value. (IE: if image (j, I) <. modelfor CROPPING leaf threshold). 5. If it is larger than threshold go to step 13. 6. If it is to a lesser extent than the threshold value, Check the variable left also equal to zero.(ie: if leftx = = 0). 7. if step 6 is true, then check ith position value greater than 10.(ie: if ( i> 10). 8. if step 7 is true, Assign leftx= i -8 and lefty= j . 9. if step 7 is false, assign leftx = 2 and lefty = j. 10.)

9 End 11. End 12. Then, Assign rightx =I and righty = j. 13. End to step 4. 14. Repeat step 3 to 13 until reaches the final status of the image (bottom right). 15. Initialize topx= 0 (zero) and topy= 0 (null), bottomx= 0, bottomy =0. 16. Start raster scanning (row wise) of the image Figure 1: Sequential Steps to Crop the image matrix from the protruding location. i. For i=2: m-1. steps: ii. For j = 2: n-1. 17. Determine for each pixel value of an image 1. Load the image data having greater than threshold value or lessthan 2. Change color to gray image. the threshold value.( ie: if image(i,j ) < threshold 3.)

10 Determine the threshold of the image ). (useostu threshold here) 18. If it is larger than threshold go to step 26. 4. Predict the first role (ex: named as findrecpoints) 19. if it is to a lesser extent than the threshold which is employed to find out the four points value,Check the variable also equal to zero.(ie: from the image to clip. if topx = = 0). Pass the loaded image and threshold value 20. if step 19 is true, then check ithposition as parameters to the subroutine. value greater than 10.(ie: if ( i> 10). This function should return the 4 values. 21. if step 7 is true, Assign topx= i -8 and topy= j.