OBJECTIVEThe objective of the image processing is to improve the pictorial information for human interpretation and handle the scene data that is automatically machine-aware. Digital image processing has a wide range of applications, such as remote sensing for transmission in commercial applications, image and data storage, medical imaging, acoustic imaging, forensics and industrial automation. Images acquired by satellites can be used to track Earth resources, geographic mapping, crop prediction, urban population, weather forecasts, floods and fire control. Spatial imaging applications include the identification and analysis of objects contained in images obtained from deep space exploration missions. Spatial imaging applications that analysis and identify the objects contained in images obtained from deep space exploration missions. There are many medical applications such as X-ray treatment, ultrasound scanning, electron microscopy, magnetic resonance imaging which manage to help human to treat illness. Image processing programs such as image enhancement and recovery are being used to process degraded or blurred images.
Image segmentation is a well-known technique for extracting information from images. Efficient segmentation is hard to failed and it may lead to a successful solution. It will significant the object by using two principle which is similarity and discontinuity. The main area of ??image processing of interest in this type of discontinuity is the detection of isolated points, lines and edges in the image. Second type of primary method is related on threshold processing, region growth, splitting and merging. Static and dynamic images is applied on the concept of a segmentation algorithm based on the discontinuity or similarity of the gray values ??of its pixels.Problem Statement1. A major trend in modern day production agriculture has been the use of data to improve farm efficiency.
The goal of this project was to explore methods to increase the accuracy of yield maps – to bring the “precision” in spatial data collection of “precision agriculture” to a whole different level.Methodology1. Boundary Detection or Segmentation and Interpretation Before further processing, proper compensations and corrections for brightness and non-uniform illumination need to be applied first. The system will check it whether the image is filtered by the filter and is it suitable for further processing. By comparing the pixel values of neighboring pixels and checking for any irrelevant significant changes, the dangerous situation can be avoided. Therefore, image analysis is supposed to see the temperature value assigned to the various color contours on the engine component image as the output. Every pixel of any point of the image must be allocated with the corresponding temperature to achieve the goal.
The closest calibration point for each pixel point on the component image and thus allocate the temperature to the location represented by that pixel have been found by developing the algorithm.2. Binary mathematical morphologyIt is a morphology that is used to process binary images and gray level images.
the morphological processing of the binary result permits the improvement of the segmentation result due to the binary images frequently result from segmentation processes on gray level images. There is a segmentation procedure which called Salt-or-pepper filtering. There is only two result which is “1” pixels in a “0” neighborhood or isolated “0” pixels in a “1” neighborhood.
The eroded binary image will be illustrated in grey and the exo-skeleton image will be shown in black in the same illustration. This procedure involves choosing small, minimum number of erosions but it is not critical numbers if it initiates a coarse separation of desired objects. The exo-skeleton which is free of “magic numbers” will perform an actual separation.3.
Gray-value mathematical morphologyIt is a morphology that is used for practical problems like shading correction. There are several techniques will be presented. First, Top-hat transform is defined that it is a isolation of gray-value that are convex can be accomplish with it. The observation can be made by observing the colors of the background which is dark or light. According to the graph, the higher the shaded image, the higher the light object. Second, Local contrast stretching which can be used in morphological operations. The original contrast in the neighborhood will control the amount of stretching that will be applied in the neighborhood. Reference1.
Giardina, C.R. and E.R. Dougherty, Morphological Methods in Image and Signal Processing. 1988, Englewood Cliffs, New Jersey: Prentice–Hall. 321.
2. Canny, J., A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986. PAMI-8(6): p. 679-698. 3.
Marr, D. and E.C.
Hildreth, Theory of edge detection. Proc. R. Soc. London Ser.
B., 1980. 207: p. 187-217. 4. Verbeek, P.W. and L.
J. Van Vliet, On the Location Error of Curved Edges in Low-Pass Filtered 2D and 3D Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994. 16(7): p. 726-733.
5. Lee, J.S.L., R.
M. Haralick, and L.S.
Shapiro. Morphologic Edge Detection. in 8th International Conference on Pattern Recognition. 1986. Paris: IEEE Computer Society. 6. Van Vliet, L.
J., I.T. Young, and A.L.D. Beckers, A Non-linear Laplace Operator as Edge Detector in Noisy Images.
Computer Vision, Graphics, and Image Processing, 1989. 45: p. 167-195. 7. Meyer, F. and S.
Beucher, Morphological Segmentation. J. Visual Comm. Image Rep., 1990. 1(1): p. 21-46. 8.
Meyer, F., Iterative Image Transformations for an Automatic Screening of Cervical Cancer. Journal of Histochemistry and Cytochemistry, 1979. 27: p. 128-135.
9. Lempereur, C., Andral, R.
, and Prudhomine, J.Y., ”Surface Temperature Measurements on Engine Components by Means of Irreversible Thermal Coating,” Science and Technology 19 (2008). 10.
Campbell, B.T., Liu, T., and Sullivan, J.P., ”Temperature Sensitive Fluorescent Paint Systems,” AIAA Paper 94-2483 (1994).
11. Sarode, M. Ladhake, S.A., and Deshmukh, P.R., ”Restoration of Gray and Color Images Using a Noise Removal Algorithm,” International Journal of Computational Science, Global Information Publisher Hong Kong 2(6):770–784 (2008).
