Skip to main content
UploadLanguage (EN)Support
BusinessMobileSocial MediaMarketingTechnologyArt & PhotosCareerDesignEducationPresentations & Public SpeakingGovernment & NonprofitHealthcareInternetLawLeadership & ManagementAutomotiveEngineeringSoftwareRecruiting & HRRetailSalesServicesScienceSmall Business & EntrepreneurshipFoodEnvironmentEconomy & FinanceData & AnalyticsInvestor RelationsSportsSpiritualNews & PoliticsTravelSelf ImprovementReal EstateEntertainment & HumorHealth & MedicineDevices & HardwareLifestyle
Ritesh Kanjee, profile picture
Uploaded byRitesh Kanjee
PPTX, PDF2,656 views

Feature detection - Image Processing

The document discusses the concept of feature detection in computer vision, detailing how the human brain recognizes patterns in visual inputs. It emphasizes the importance of blobs, as well as other features like lines and corners, in detecting and measuring significant characteristics of objects within images. The document also outlines a course using LabVIEW to teach image processing fundamentals and the development of vision-based applications.

Scienceā—¦
Basic Feature Detection The human brain does a lot of pattern recognition to make sense of raw visual inputs. o After the eye focuses on an object, the brain identifies the characteristics of the object ā€”such as its shape, color, or textureā€” and then compares these to the characteristics of familiar objects to match and recognize the object. o In computer vision, that process of deciding what to focus on is called feature detection. o A feature can be formally defined as ā€œone or more measurements of some quantifiable property of an object, computed so that it quantifies some significant characteristics of the objectā€ (Kenneth R. Castleman, Digital Image Processing, Prentice Hall, 1996). o Easier way to think of it: a feature is an ā€œinterestingā€ part of an image.
Good Vision System Characteristics o A good vision system should not waste timeā€”or processing powerā€”analyzing the unimportant or uninteresting parts of an image, so feature detection helps determine which pixels to focus on. o We will focus on the most basic types of features: blobs, lines, circles, and corners. o If the detection is robust, a feature is something that could be reliably detected across multiple images.
Detection criteria o How we describe the feature can also determine the situations in which we can detect the feature. o Our detection criteria for the feature determines whether we can: ā€¢ Find the features in different locations of the picture (position invariant) ā€¢ Find the feature if itā€™s large or small, near or far (scale invariant) ā€¢ Find the feature if itā€™s rotated at different orientations (rotation invariant)
Blobs Blobs are objects or connected components, regions of similar pixels in an image. The examples are as follows: ā€¢ A group of brownish pixels together, which might represent food in a pet food detector. ā€¢ A group of shiny metal looking pixels, which on a door detector would represent the door knob. ā€¢ A group of matte white pixels, which on a medicine bottle detector could represent the cap. o Blobs are valuable in machine vision because many things can be described as an area of a certain color or shade in contrast to a background.
Finding Blobs Morphological operators such has thresholding can be used to find objects that are lightly colored in an image. If no parameters are specified, the function tries to automatically detect what is bright and what is dark.
Blob Measurements After a blob is identified we can measure a lot of different things: o Area o Width and height o Find the centroid o Count the number of blobs o Look at the color of blobs o look at its angle to see its rotation o find how close it is to a circle, square, or rectangle ā€”or o compare its shape to another blob
Blob Detection And Measurement 1. Blobs are most easily detected on a binarized image. 2. Returns a Feature Set: ā€¢ List of features about the blobs found ā€¢ Has a set of defined methods that are useful when handling features 3. It draws each feature in the Feature Set on top of the original image and then displays the results. After the blob is found, several other functions provide basic information about the feature, such as its size, location, and orientation.
Vision-Based Apps o App 3 : Blob Detection o App4 : Measuring Blobs
If you would like to Learn More on Image Processing Course using LabVIEW Course Description Learn the basic concepts, tools, and functions that you will need to build 9 fully functional Vision-based Apps with LabVIEW and LabVIEW Vision Development Toolkit. ā€¢ Together we will build a strong foundation in Image Processing with this tutorial for beginners. ā€¢ LabVIEW Vision Development Toolkit Download and Installation ā€¢ Basic Feature Detection ā€¢ Circle, Color and Edge Detection Algorithms ā€¢ Advance Feature Detection - Pattern Matching, Object Tracking, OCR, Barcodes Save over $44 and get it for Only $15! Use Coupon Code SlideShare on udemy.com ā€¢ Limited Coupons Left!
If you would like to Learn More on Image Processing Course using LabVIEW https://www.udemy.com/learn-computer-vision-machine-vision-and- image-processing-in-labview/?couponCode=SlideShare Starting with the installation of the LabVIEW Vision Development Toolkit, this course will take you through the main and fundamental Image Processing tools used in industry and research. At the end of this course you will be able to create the following Apps: ā€¢ App 1 - Counting M&Ms in an Image, ā€¢ App 2 - Color Segmentation and Tracking, ā€¢ App 3 - Coin Blob detection ā€¢ App 4 - Blob Range Estimation ā€¢ App 5 - Lane Detection and Ruler Width Measurement ā€¢ App 6 - Pattern or Template Matching to detect Complex Objects ā€¢ App 7 - Object Tracking ā€¢ App 8 - Bar code Recognition ā€¢ App 9 - Optical Character Recognition (OCR) With these basic and advanced algorithms mastered, the course will take you through the basic operation of the theory behind each algorithm as well how they applied in real world scenarios.