Abstract
Image analysis has many practical applications and proper representation of image content is its crucial element. In this work, a novel type of representation is proposed where an image is reduced to a set of highly sparse matrices. Equivalently, it can be viewed as a set of local features of different types, as precise coordinates of detected keypoints are given. Additionally, every keypoint has a value expressing feature intensity at a given location. These features are extracted from a dedicated convolutional neural network autoencoder. This kind of representation has many advantages. First of all, local features are not manually designed but are automatically trained for a given class of images. Second, as they are trained in a network that restores its input on the output, they may be expected to minimize information loss. Consequently, they can be used to solve similar tasks replacing original images; such an ability was illustrated with image classification task. Third, the generated features, although automatically synthesized, are relatively easy to interpret. Taking a decoder part of our network, one can easily generate a visual building block connected with a specific feature. As the proposed method is entirely new, a detailed analysis of its properties for a relatively simple data set was conducted and is described in this work. Moreover, to present the quality of trained features, it is compared with results of convolutional neural networks having a similar working principle (sparse coding).
Highlights
Images are typically represented using regular grids of pixels
To enforce sparse coding, which allows us to determine the precise localization of these features, we propose a specific neural network architecture with additional filtering layers and a unique adjustment of the training objective
Instead of using the global statistics of the convolutional neural networks (CNN) layer output, we propose a method that focuses on local properties
Summary
The information about image content is kept both in pixels’ attributes (color channels) and, which seems to be even more important, in their spatial distribution This kind of representation, natural for humans, has at least one crucial drawback: It significantly complicates the design of effective computer algorithms able to accomplish tasks which are relatively easy for our visual system. The nature of this problem lies in the huge number of image elements and the variety of their possible distributions, and in the fact that humans do not consciously operate on individual pixels. The second one, instead of direct implementation, engages machine learning for this purpose
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
