AbstractSmart forming is a growing research field in agriculture image based applications. In this paper we are identifying the different size of oranges and count the number of oranges fruits in an image. In this proposed method we use Circular Hough Transform Algorithm to recognize the oranges to count the number of oranges are there in the images and further we find the radius of them.
Based on the radius value, the oranges of different sizes are classified. The results shows that the Circular Hough Transform Algorithm is the best method to identify the circle based objects.Keyword: circle detection, Hough Transform algorithm and Orange fruit counting. IntroductionIn recent years development in machine vision and supporting technologies has indicated in general acceptance of feasibility and profitability of implementing visual inspecting system in quality assurance in food processing industries 1. Orange shape detection is one of the challenging task in machine intelligence and computer vision because it has various sizes in various stages.
Fruit detection and counting is also a challenging task. One of the most challenging tasks of an image processing nowadays is feature extraction. In the real world applications an objects of interest may come in different sizes and shapes, not pre-determined one. In this work we use Circle Hough Transform algorithm to extract the size of that oranges by measuring the radius and center of that circle and also we can count the number of oranges are there in that.
Related workThe author Neelu Jain has represents algorithm for recognition of the coins of different denomination .In that method they uses canny edge detection to generate edge map , then uses CHT (Circular Hough transform) to recognize the coins and further find the radii of them. Based on the radius of the coin, the coins of different denomination are classified 1. The CHT is used for detecting the coins of different denominations, so a suitable range for radius of the coins can be defined 1. The CHT has been used in several researches in detecting iris and pupil boundaries for face recognition, fingertips position detection and automatic ball recognition. The author marcin smereka proposes a method that is designed for the detection of demanding (noisy, not clearly distinguishable) circular objects can be applied, fixing some data with domain-specific values, to any real industry images 2.III.
Circular Hough Transform Algorithm The Circular Hough Transform (CHT) based algorithm for finding circles in images. This approach is used because of its robustness in the presence of noise, occlusion and varying illumination. The CHT is not a rigorously specified algorithm; rather there are a number of different approaches that can be taken in its implementation.
However, by and large, there are three essential steps which are common to all.1. Accumulator Array Computation.Foreground pixels of high gradient are designated as being candidate pixels and are allowed to cast ‘votes’ in the accumulator array. In a classical CHT implementation, the candidate pixels vote in pattern around them that forms a full circle of a fixed radius. Figure 1a shows an example of a candidate pixel lying on an actual circle (solid circle) and the classical CHT voting pattern (dashed circles) for the candidate pixel.Figure 1: classical CHT voting pattern2.
Center EstimationThe votes of candidate pixels belonging to an image circle tend to accumulate at the accumulator array bin corresponding to the circle’s center. Therefore, the circle centers are estimated by detecting the peaks in the accumulator array. Figure 1b shows an example of the candidate pixels (solid dots) lying on an actual circle (solid circle), and their voting patterns (dashed circles) which coincide at the center of the actual circle.3.
Radius EstimationIf the same accumulator array is used for more than one radius value, as is commonly done in CHT algorithms, radii of the detected circles have to be estimated as a separate step.The method provides two algorithms for finding circles in images: Phase-Coding (default) and Two-Stage. Both share some common computational steps, but each has its own unique aspects as well.The common computational features shared by both algorithms are as follow: Use of 2-D Accumulator Array:The classical Hough Transform requires a 3-D array for storing votes for multiple radii, which results in large storage requirements and long processing times. Both the Phase-Coding and Two-Stage methods solve this problem by using a single 2-D accumulator array for all the radii.
Although this approach requires an additional step of radius estimation, the overall computational load is typically lower, especially when working over large radius range. This is a widely adopted practice in modern CHT implementations. Use of Edge PixelsOverall memory requirements and speed is strongly governed by the number of candidate pixels. To limit their number, the gradient magnitude of the input image is threshold so that only pixels of high gradient are included in tallying votes. Use of Edge Orientation Information:Another way to optimize performance is to restrict the number of bins available to candidate pixels.
This is accomplished by utilizing locally available edge information to only permit voting in a limited interval along direction of the gradient (Figure 2).Figure 2: Voting mode: multiple radii, along direction of the gradientThe two CHT methods employed by function imfindcircles fundamentally differ in the manner by which the circle radii are computed. Two-StageRadii are explicitly estimated utilizing the estimated circle centers along with image information. The technique is based on computing radial histograms; see references 2 and 3 for a detailed explanation 123. Phase-CodingThe key idea in Phase Coding 3 is the use of complex values in the accumulator array with the radius information encoded in the phase of the array entries.
The votes cast by the edge pixels contain information not only about the possible center locations but also about the radius of the circle associated with the center location. Unlike the Two-Stage method where radius has to be estimated explicitly using radial histograms, in Phase Coding the radius can be estimated by simply decoding the phase information from the estimated center location in the accumulator array123.IV. ResultsIn this work firstly we need to do image accusation. In that we took the images of oranges as an input. The acquired images may have different sizes so that we need to resize it to the appropriate format which is comfortable for your work.
After the image resizing process we need to apply edge detection techniques to identify the edges of an image. On that image we apply circular Hough transform method to identify the shape and size of an image. In this algorithm we have to calculate the center and radius value of each circle with the help of the sensitive value.
In this work we will use 0.98 as our sensitivity value. With the help of those values we can identify the size and shape of an orange image and count on itSome of the radius values are:23.
90 22.22 21.94 21.8520.5723.4322.9522.
25023.895V. ConclusionThe oranges of different sizes and shape can be recognized based on the radius of the circle.
When orange are placed on a plain surface, the edges of the oranges are easily traced and the HT has a much higher chance of success. By using the canny edge detector in conjunction with CHT, the coordinates of the shape are evaluated. The proposed system can be used to identify the shape and size of oranges by using Circular Hough Transform methods.
The problem arises if the orange image is captured from a distance and the image tends to be small. Besides that, some of the ranges are overlapped. These restrictions make the detection process difficult. Future work may include detection of several shape features that are overlapped with each other.VI.
References1 Dr. Neelu Jain and Neha Jain, “Coin Recognition Using Circular Hough Transform”, “International Journal of Electronics Communication and Computer Technology (IJECCT”, Vol. 2, Issue 3 (May 2012) 2 Marcin Smereka, Ignacy Dule,” Circular Object Detection Using a Modified Hough Transform”,Int. J.
Appl. Math. Comput. Sci., Vol. 18, Issue 2008.
3 T.J Atherton, D.J.
Kerbyson. “Size invariant circle detection.” Image and Vision Computing. Volume 17, Number 11, 1999, pp. 795-803.4 H.K Yuen, .J.
Princen, J. Illingworth, and J. Kittler. “Comparative study of Hough transform methods for circle finding.” Image and Vision Computing.
Volume 8, Number 1, 1990, pp. 71–77.5 E.R. Davies, Machine Vision: Theory, Algorithms, Practicalities. Chapter 10. 3rd Edition.
Morgan Kauffman Publishers, 20056 International Journal of Electronics Communication and Computer Technology (IJECCT) Volume 2 Issue 3 ( May 2012) ISSN:2249-7838 IJECCT . rminMinimum search radiusrmaxMaximum search radiusractualRadius of the circle that the candidate pixel belongs tocminCenter of the circle of radius rmincmaxCenter of the circle of radius rmaxcactualCenter of the circle of radius ractual