ABSTRACT

Keywords:Speeded Up Robust Features(SURF), OpenCV, emguCV, Detection, Tracking,

Matching Points and Lines


In this paper, we present a technology which is a computer vision is that there presentation in the
updation form, OpenCV-Open Source Computer Vision Library we are using as reference for
performing our execution and demonstrate the result. The Object Character Recognition Is the
technology which can recognize and analyse the specific object and that can get the out as text
which is the editable form. The Object may be paper, picture which might any format and real-
time desktop or anything else. More recently, the term Intelligent Character Recognition
(ICR) has been used to describe the process of interpreting image data, in particular
alphanumeric text. Intelligent Character Recognition (ICR) is the module of OCR that has the
ability to turn images of hand written or printed characters into ASCII data. Sometimes OCR is
known as ICR. ICR and OCR are recognition engines used with imaging while OMR is a
data collection technology that does not require a recognition engine. Therefore, basically
OMR cannot recognize hand-printed or machine-printed characters. However, in the OCR
technology, answer for question in tick or mark is also known as OCR.We are here
defining that the suphrial system which works like intelligence. And also we define the
representation of structure and algorithm in that included. In this paper, we present a original
scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded
Up Ro- bust Features). It approximates or even out performs previously proposed schemes
with respect to repeatability, distinctiveness, and robustness, yet can be computed and
compared much faster. This is achieved by relying on integral images for image convolutions
by building on the strengths of the leading existing detectors and descriptors and by
simplifying these methods to the essential. Feature matching is at the base of many computer
vision problems, such as object recognition or structure from motion. Current methods rely
on costly descriptors for detection and matching. In this paper, we propose a very fast binary
descriptor based on BRIEF, called ORB(object recognized blob), which is rotation invariant
and resistant to noise. We demonstrate through experiments how ORB is at two orders of
magnitude faster than SIFT, while performing as well in many situations. The efficiency is
tested on several real-world applications, including object detection and patch-tracking on a
smart phone This leads to a combination of original detection, description, and matching
steps. The paper presents experimental results on a standard evaluation set, as well as on
imagery obtained in the context of a real-life object recognition application. Its all over show
SURFs stronger performance. Also we define the real-time object matching implementation
in that paper.