Image classification
Download as PPTX, PDF3 likes2,366 views
This document discusses image classification. It defines image classification as assigning pixels in an image to categories or classes of interest based on features extracted from the image. It describes classification as a process that maps unlabeled instances to predefined classes. Supervised learning involves a teacher to form mappings from data to classes, while unsupervised learning explores data distributions without a teacher. The document outlines the process of image classification which involves training a classifier on labeled images to learn class representations, then evaluating it on unlabeled test images. Applications of image classification include medical imaging, urban planning, and visual search.
Image classification
- 1. Image Classification Ali A. Jalil
- 2. What is Computer Vision? • Here are a couple of formal textbook definitions: • “the construction of explicit, meaningful descriptions of physical objects from images” (Ballard & Brown, 1982) • “computing properties of the 3D world from one or more digital images” (Trucco & Verri, 1998) • “to make useful decisions about real physical objects and scenes based on sensed images” (Sockman & Shapiro, 2001)
- 3. Classification •A structured model that maps unlabeled instances to finite set of classes • is the process of assigning value in a data set to a predefined label (Categories) •labeled data set shared a common properties )features).
- 4. Classifier A classifier: Algorithm that produces class labels as output, from a set of features of an object. • A classifier, for example, is used to classify certain features extracted from a face image and provide a label (an identity of the individual) • ANN • Decision Tree • Naive Bayes • Etc..
- 5. Types of Learning • Supervised: Learning process designed to form a mapping from one set of variables (data) to another set of variables (information classes). A teacher is involved in the learning process
- 6. Types of Learning • Unsupervised learning: Learning happens without a teacher. Exploration of the data space to discover the scientific laws underlying the data distribution.
- 7. Supervised vs. Unsupervised Classifiers • Supervised classification generally performs better than unsupervised classification IF good quality training data is available • Unsupervised classifiers are used to carry out preliminary analysis of data prior to supervised classification
- 8. Image classification • Image classification: refers to a process in computer vision that can classify an image according to its visual content. • Assigning pixels in the image to categories or classes of interest. • is the process of predicting a specific class, or label, for something that is defined by a set of data points.
- 9. Image Classification • The problem of image classification goes like this: Given a set of images that are all labeled with a single category. • we’re asked to predict these categories for a novel set of test images and measure the accuracy of the predictions. • There are a variety of challenges associated with this task, including viewpoint variation, scale variation, intra-class variation, image deformation, image occlusion, illumination conditions, and background clutter.
- 10. Image Classification • Based on a preprocess of image processing, which is Feature Extraction, the classifier work to gathering images are having same features in one Category to give them same label.
- 11. Classification Process • Each classification process contain following: • Classifier • Data set : Training data set and Test Data Set • Our input is a training dataset that consists of N images, each labeled with one of K different classes. • Then, we use this training set to train a classifier to learn what every one of the classes looks like. • In the end, we evaluate the quality of the classifier by asking it to predict labels for a new set of images that it’s never seen before. We’ll then compare the true labels of these images to the ones predicted by the classifier.
- 12. Application of Image Classification • Classify Medical Images (e.g., tumor is cancer or not). • Urban planning (By using satellite images to identify lands). • Images collection and reordering. • Visual Search for Improved Product Discoverability • And more….
- 13. Thank You