Counting Objects using Convolution based Pattern Matching Technique

Abstract

In this paper, counting objects techniques are proposed for fast pattern matching algorithm based on normalized cross correlation and convolution technique which are widely used in image processing application. Pattern matching can be used to recognize and/or locate specific objects in an image. It is one of the emerging areas in computational object counting. In this paper, introduces a new pattern matching technique called convolution based on pattern matching algorithm. Many different pattern matching techniques have been developed but more efficient and robust methods are needed. The pattern matching algorithm is used to identify the patterns similar present in image. With the patterns, identify the similarity measures of the given pattern to count the object present in the given image. An experimental evaluation is carried out to estimate the performance of the proposed efficient pattern matching algorithm for remote sensing as well as common images in terms of estimation of execution times, efficiency and compared the results with an existing conventional methods.

ASSAS: An automatic smart students attendance system based on normalized cross-correlation

“…Our system used Arduino and counting objects. Thus, the similarities between cited work [1] and [23] are the Arduino and counting object techniques. Basically, the mechanism of the developed system in this paper is explained through the following scenario: When the student is present inside the classroom, the system takes an image from Arduino's camera that is located inside the classroom.…”

“…There are many techniques for face recognition and detection, for example, local binary patterns (LBP) [8,9], principal component analysis (PCA) [10,11], a combination of PCA, wavelet, and support vector machines (SVM) [12], local binary pattern histogram (LBPH) [13], independent component analysis (ICA) [14,15], eigenfaces [16], and linear discriminant analysis (LDA) [17,18], SVM [19,20], combining fast discrete curvelet transform (FDCvT) and invariant moments with SVM and deep learning technology [21,22]. Dharpure et al [23] proposed a system that utilized counting objects techniques for a fast template matching process based on the normalized cross-correlation (NCC) algorithm. The template matching algorithm utilized to identify a similar template present in the image.…”

“…Our system is similar to cited work in [1] and [23]. To illustrate, cited work [1] used Arduino, and cited work [23] used counting object with CNN. Our system used Arduino and counting objects.…”

Determination of the Number of Objects through Weight and Image Processing

“…Pattern matching as a method for identifying and locating specific objects, regardless the background or other objects present in the image, has also been a popular choice in literature [9,10]. Neural networks have also been successfully applied to object detection when there are different types of objects to be counted separately, or when the objects of interest must be identified amidst several other objects that are not to be considered.…”