Alison's New App is now available on iOS and Android! Download Now

Computer Vision - Visual Features and Representations

In this free online course, learn the approaches in establishing feature correspondences across different images in CV.

Publisher: NPTEL
Feature detection is a powerful method for computing abstractions of image information and making local decisions at every image point. This free online course illustrates the algorithms used for detecting various features from the images and the method of extracting meaningful information for recognising the objects. Start learning about the process of establishing a dense set of correspondence for constructing 3D model images.
Computer Vision - Visual Features and Representations
  • Duration

    4-5 Hours
  • Students

  • Accreditation






View course modules


This free online course explains the practical approaches in detecting and establishing feature correspondences across different images. It begins with the conceptual idea of detecting edges on an image, using various mathematical methods. You will explore how edge detection is the first step in recovering information from images and how the directional change in the intensity or colour in an image is used for detecting edges. The procedure for detecting blobs and corners in an image are explained. You will be taught how the circularly symmetric feature of Laplacian of Gaussian is used for detecting the regions of an image in which some properties are constant. Alongside this, how the corner detection method is used to extract information about the features and infer an image’s contents are also described. The most recently used methods in detecting various kinds of edges and blobs in an image are highlighted.

Next, the course illustrates the Haris Corner Detector’s scale-invariant nature by analysing the images’ key points at different scales. You will discover the image pyramids’ role in performing tasks such as image blending and coarse-to-fine correspondence search to accelerate certain operations. This will include analysing the specific frequency content in the image in particular directions in a localised region around the point or region of analysis.The role of the scale-invariant feature transform in transforming the image data into scale-invariant key point coordinates is discussed. You will be taught about the process of extracting keypoints and matching the keypoints with their corresponding locations in the images. The scale-invariant features are formed by computing the gradient at each pixel in a window around the detected keypoint, using the appropriate level of the Gaussian pyramid.

Finally, the course highlights the various techniques that have been developed for image segmentation. These include algorithms based on active contours and level sets, region splitting and merging, mean shift, normalised cuts, and binary Markov random fields solved using graph cuts. In addition to this, representing an image in terms of clusters of pixels that belong together for locating objects and boundaries in images, is discussed. You will discover how the shape context and maximally stable extremal regions are used for recognising objects based on their contours and for applications that require affine invariance. Lastly, the course explains how the human visual system interprets the subtle variations in transparency and shading in the images by correctly segmenting the object from its background. Computer Vision-Visual Features and Representations is an informative course that will interest those studying Computer Science or those interested in these topics. Why wait? Sign up today and start learning about this leading computer vision technique for extracting vital information from various parts of the image.

Start Course Now