This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.
Image Processing is an effective tool to enhance and retrieve the information Present in images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-day life for various applications. There are so many techniques and algorithms which are in used in various applications like medical, remote sensing, Forensic Studies, Textiles, Material Science etc. Image processing systems are becoming popular due to easy availability of powerful personnel computers, large size memory devices, graphics software's.
Agriculture sector is one of essential sector of an Indian economy, and our major portion of population is dependent on it. Image processing is one of the emerging techniques and it makes important contribution towards evolution of agriculture system. By using image processing system it is possible to reduce error, quick decision making related to farm input .this in turn will provide support for a sustainable agriculture economy.
II. Image processing
For any image processing system consist of two main part i.e. image acquisition system, image processing system. Image acquisition system collect the image on which it has to work, and further it is processed by using image processing algorithms. In agricultural
remote sensing used for different purpose, and we can take the images from remote sensors as the input image or raw data for the analysis purpose. This remote sensing data further processed using software which is based on several algorithms.
Image processing includes image preprocessing, enhancement, segmentation which ex tract the information from the images .image processing involves, Image Preprocessing improve the image in ways that increase the chances for success of the other processes. It involves following operations, scaling rotation, reduction, magnification. image preprocessing make image the suitable for further operations. Image enhancement is the improvement of digital image quality (wanted e.g. for visual inspection or for machine analysis), without knowledge about the source of degradation. Image segmentation-is used to partitions an input image into its constituent parts or objects. Image representation converts the input data to a form suitable for computer processing. Image description extract features that result in some quantitative information of interest or features that are basic for differentiating one class of objects from another. Image recognition assigns a label to an object based on the information provided by its descriptors.
III. Applications based on Algorithms
There are several image processing algorithms like k-mean algorithms, morphological operation, enhancement algorithms that can be used for agricultural image analysis purpose.
Image enhancement Technique used to define the clear cut boundaries of any agricultural land. For this purpose we can use boundary detection, edge detection algorithms. For image enhancement we can use histogram equalization also.
We can apply k-mean algorithm (2) for the image classification or grading purpose-mean algorithm clusters the regions possessing similar characteristics. We can categories the yield of agricultural output based on the shape, size and color.iit can be used for grading of strawberry form different regions.
weed coverage present in the main crops can be detected by using Morphological operations .it includes s dilation and erosion of an image in this we erode the some regions which are below the structuring element limit and the n dilate the regions of interest .in this manner we can determine the determine the presence of weeds .
IV. Image enhancement
For the detection of boundaries of any agricultural land we have used sobel and canny edge detectors .we have taken raw data or image from the sensing device converted it into grey scale by defining it minimum and maximum value of pixels. After this edge detectors are applied to that image.
( a) (b)
Figure1: (a) original image, (b) grey scale image, (c) & (d) image after edge detection
IV. Algorithms Used:
In this paper we have discussed two algorithms one is based on k-mean clustering and other one is based on morphological operations .K-Means Clustering, clusters the image data set into k subsets of pixels; each subset has a center value which is the average of all pixels in the subset, thus k subsets resulted in k centers total. A pixel is grouped into a subset by first calculating the distances between the pixel and each center, and then the pixel is grouped into the subset that has the closest center. After one pass through the image, error is calculated, and the clustering process is stopped when the error converged to a value; error is the sum of the squared distances between all pixels in a subset and the subset's center. Morphological operations process the images based on shapes. Morphological operations apply a structuring element to an input image, creating an output image of the same size. In a morphological operation, the value of each pixel in the output image is based on a comparison of the corresponding pixel in the input image with its neighbors. By choosing the size and shape of the neighborhood, you can construct a morphological operation that is sensitive to specific shapes in the input image.
V. K-mean algorithm
The Clustering algorithm implemented for grayscale images consists of following steps:
Read in the image file and store image data in a matrix array
Find the minimum and maximum pixel values of the input image
Initialized K centers with the results from step 2
for each pixel calculate its distance to each center cluster the pixel into the subset that has
Calculate new K centers; each new K center is the average of all pixel values in its subset
Calculate new error, the sum of the squared distances between all pixels in a subset and the subset's center
Repeat steps 4 to 6 until error converged to a value
Write the output image to an image file
VI. Morphological algorithm
Morphology is a broad set of image processing operations that process images based on shapes. Morphological operations apply a structuring element to an input image, creating an output image of the same size. In a morphological operation, the value of each pixel in the output image is based on a comparison of the corresponding pixel in the input image with its neighbors. By choosing the size and shape of the neighborhood, you can construct a morphological operation that is sensitive to specific shapes in the input image.
The most basic morphological operations are dilation and erosion. Dilation adds pixels to the boundaries of objects in an image, while erosion removes pixels on object boundaries. It can be achieved in following ways:
Capture an image store it in digital form.
Convert the captured image into binary form so that all pixels have values of 0 or1
Use structuring element to erode the image and then dilate it.
VII. Result and discussion
We have taken some sample images and tried to find out the object of interest from it and also highlighted the affected area by pest on leaf by means of image processing
In the figure2 we can see the individual object by using morphological operations. Emphasis put on one object and it is dilated and clearly visible in processed image.
Figure2: (a) original image, (b) object identified after Processing
We have also use distance transform method in which we can highlight the affected area. In figure 3 we can see the original image and image after processing. The affected area by pest is more darken then the other surface of leaf.
Figure3: (a) original image, (b) object identified after morphological operation
By using image enhancement technique we can define the clear cut edges and boundaries of any image .morphological operations can highlights the image information either background information or actual object in image. This is helpful in determine the main crop area excluding the weeds in crop. This can be seen in figure 1.
We have implemented several functions of MATLAB in order to find out the some solutions associated with agriculture sector. There is possibility to distinguish land area using some filtering and enhancement method based on images obtained from remote sensors. We can also highlight and calculate the affected area by certain pest on crop. This will be helpful in determining the extent of degradation in crop yield and we can also suggest the concentration of pesticides as a remedial solution. In this paper we have taken one small leaf but it can be made applicable to whole crop.
Based on the processed image we can also determine the presence of weed (unwanted plants in main crop) in the main crop. There may be several other algorithms which can be applied .Hence image processing can be made useful for sorting the problems in agriculture sector by processing an image that is collected by either remote sensors or any image acquisition systems.
 Gonzalez Rafael C., Richard E woods, "Digital Image Processing", 2nd Edition
Xu Liming, Zhao Yanchao,2010, "Automated strawberry grading system based on image processing", Science Direct -Computers and Electronics in Agriculture 71, 2010 ,pp 32-39
 Imran Ahmed, Syed shah, Md Islam, Awais Adnan, 2007, " A Real time specific weed recognition system using statistical methods" , World academy of science, engineering and technology, pp 143-145.
 Muhammed H. Siddiqi, Irshad Ahmed, Suziah Sulaiman, 2009, "Weed recognition based erosion and dilation segmentation algorithm", IEEE International conference on education technology and computer, pp 224-228
 William K. Pratt: DIGITAL IMAGE PROCESSING, 1991 by John Wiley & Sons, Inc
 S. Beucher and F. Meyer, Mathematical morphology in image processing. The morphological approach to segmentation: the watershed transformation (E. Dougherty, ed.),M. Dekker, 1993.
 S. Beucher, Mathematical Morphology and its Applications to Image Processing. Watershed, hierarchical segmentation and waterfall algorithm (J. Serra and P.Soille, eds.), Eds. Kluwer Acad. Publ., Dordrecht, 1994.
 Muhammad Shahzad,Shiraz Latif," Efficient Image Enhancement Techniques" Journal of Information & Communication Technology
Vol. 3, No. 1, (Spring 2009) 50-55
 Atul, Rochak, Saini"Simulation of Image Enhancement Techniques using MATLAB,"Proceedings of the First Asia International Conference on Modelling & Simulation, pp. 2007Page(s): 296- 301.
 Morphological Image Processing:Basic concept Spring 2009 ELEN 4304/5365 DIP 1by Gleb V. Tcheslavski: email@example.com
Chun-chieh Yang, Shiv O Prasher, J Landry, H.S. Ramaswamy, 2003, " Development of an image processing system and fuzzy algorithm for site specific herbicide applications" Precision agriculture,4, pp 5-18.
 Chun-chieh Yang, Shiv O Prasher, J Landry, H.S. Ramaswamy and A. Ditommaso, 2000, " Application of artificial neural networks in image recognition and classification of crop and weeds", Canadian agricultural engineering, vol 42,no 3, pp 147-152.
 Xu Liming, Zhao Yanchao,2010, "Automated strawberry grading system based on image processing", Science Direct -Computers and Electronics in Agriculture 71, 2010 ,pp 32-39
 Anderson Rocha, Daniel C. Hauagge, Jacques Wainer, Siome Goldenstein, 2010, "Automatic fruit and vegetable classification from images", Science Direct -Computers and Electronics in Agriculture 70, pp96-104.