System and method for recognizing offensive images

a technology of offensive images and categorizing methods, applied in image analysis, instruments, computing, etc., can solve the problems of only effective text-based analysis and categorizing, only offensive to view pornographic images, and legal liability issues, so as to achieve reliable and efficient recognizing offensive images

US20160275343A1Inactive Publication Date: 2016-09-22CA TECH INC
12 Cites 11 Cited by

Patent Information

Authority / Receiving Office
US · United States
Patent Type
Applications(United States)
Current Assignee / Owner
Publication Date
2016-09-22
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

According to one aspect, a method for categorizing at least one image includes obtaining the at least one image and mapping the at least one image to at least a first grid. The first grid is a two-dimensional grid that includes a plurality of cells. The method also includes characterizing the first grid, wherein categorizing the first grid includes determining whether the first grid is indicative of an offensive characteristic, and identifying the at least one image as offensive when it is determined that the first grid is indicative of the offensive characteristic. When it is determined that the first grid is not indicative of the offensive characteristic, the at least one image is identified as not offensive.
Need to check novelty before this filing date? Find Prior Art

Description

BACKGROUND

[0001] 1. Field of Invention

[0002] The present disclosure relates generally to categorizing images. More particularly, the present disclosure relates to precisely and efficiently detecting pornographic images located on the Internet or within email communications.

[0003] 2. Description of the Related Art

[0004] Offensive images, e.g., pornographic images, are often available on the Internet, and are often sent in email communications to unwitting parties. Pornography is prevalent on the Internet, both in legal and illegal forms. Some parties may find it offensive to view pornographic images. For other parties, viewing pornographic images may result in legal liability issues.

[0005] Images may be categorized using a text-based analysis and categorization. While text-based analysis and categorization may be effective in categorizing pornographic images, a text-based analysis and categorization is generally only effective when a significant amount of text is included in a web page or...

Examples

Embodiment Construction

[0021]Example embodiments of the present invention are discussed below with reference to the various figures. However, those skilled in the art will readily appreciate that the detailed description given herein with respect to these figures is for explanatory purposes, as the invention extends beyond these embodiments.

[0022]Pornographic images are prevalent on the Internet, in both legal and illegal forms. Many individuals consider pornographic or other offensive images to be offensive, and would prefer to reduce the likelihood that they may accidentally access the images. For other parties, such as those who are part of a corporation, access to pornographic or other offensive images may result in legal liability issues for the corporation. As such, the ability to identify pornographic images or, more generally, offensive images is desirable.

[0023]Offensive images, as mentioned above, generally include pornographic images. In addition, offensive images may also include, but are not ...