Sparse High-Dimensional Representations and Large Mar- gin Classifiers for Image Retrieval
نویسندگان
چکیده
The Problem: There has been an explosion of content on the Web. In the very near future, images, video and virtual reality will be available on demand much as text is now. Somehow an interested user must be able to find the images or video of interest. For example a user may wish to scan a travel documentary for images of distinct locations and objects, like “Buddhist temples”, “Gothic cathedrals”, or “statues on horseback”.
منابع مشابه
Image Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کاملBoosting Sparse Representations for Image Retrieval
In this thesis, we developed and implemented a method for creating sparse representations of real images for image retrieval. Feature selection occurs both offline by choosing highly selective features and online via “boosting”. A tree of repeated filtering with simple kernels is used to compute the initial set of features. A lower dimensional representation is then found by selecting the most ...
متن کاملLearning Document Image Features With SqueezeNet Convolutional Neural Network
The classification of various document images is considered an important step towards building a modern digital library or office automation system. Convolutional Neural Network (CNN) classifiers trained with backpropagation are considered to be the current state of the art model for this task. However, there are two major drawbacks for these classifiers: the huge computational power demand for...
متن کاملSound Retrieval and Ranking Using Sparse Auditory Representations
To create systems that understand the sounds that humans are exposed to in everyday life, we need to represent sounds with features that can discriminate among many different sound classes. Here, we use a sound-ranking framework to quantitatively evaluate such representations in a large-scale task. We have adapted a machine-vision method, the passive-aggressive model for image retrieval (PAMIR)...
متن کاملSound Ranking Using Auditory Sparse-Code Representations
The task of ranking sounds from text queries is a good test application for machine-hearing techniques, and particularly for comparison and evaluation of alternative sound representations in a large-scale setting. We have adapted a machine-vision system, “passive-aggressive model for image retrieval” (PAMIR) [2], which efficiently learns, using a ranking-based cost function, a linear mapping fr...
متن کامل