Method for detecting facial expressions of a portrait photo by an image capturing electronic device

• US 7,715,598 B2
• Filed: 07/25/2006
• Issued: 05/11/2010
• Est. Priority Date: 07/25/2006
• Status: Active Grant

• Current Assignee: ArcSoft, Inc.
• Original Assignee: Arsoft Incorporated
• Inventors: Wang, Jin, Li, Shu
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Koziol; Stephen R
• Application Number:
  US11/492,076
• Publication Number:
  US 20080025576A1
• Time in Patent Office: 1,386 Days
• Field of Search: 382/118, 382/159, 382/298, 348/E5.042
• US Class Current: 382/118
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/175 Static expression
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/64 Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image

Abstract

In a method for detecting facial expressions of a portrait photo by an image capturing electronic device, a face captured in the portrait photo is detected. The position and range of the opened and closed facial features are detected, and the facial features within an identified range are magnified according to a specific proportion. A patch of facial features and their surroundings within a specific range is cut according to the magnified identified range, so that the patch can show a change of facial expressions and a specific range of their surroundings. A facial feature classifier is trained by a specific number of opened and closed facial feature samples based on the Adaboost algorithm and used for detecting the facial features in the patch to determine whether the facial feature is situated at an opened state or a closed state.

Claims

1. A method for detecting facial expressions of a portrait photo by an image capturing electronic device, being used for an electronic image capturing device, and comprising the steps of:

capturing a current image;

detecting a position and a range of a human face on a portrait photo;

detecting a position and a range of an opened facial feature or a closed facial feature such as an eye or a mouth;

magnifying an identified range of a position of said facial feature according to a predetermined proportion, and cutting said facial feature and a patch within a predetermined surrounding range by said magnified identified range, and said patch being capable of showing a picture with a change of said facial feature and a facial expression in said predetermined surrounding range; and

training a facial expression detector by a predetermined number of opened or closed facial feature samples, and detecting an opened state or a closed state of said facial feature in said patch to determine whether or not said facial feature is situated at an opened state or a closed state.

2. The method of claim 1, further comprising a step of issuing a warning signal when said facial feature in said patch is determined to be situated at a closed state.

3. The method of claim 1, further comprising the steps of permitting a user to press a shutter of said electronic image capturing device to capture a portrait photo and saving said portrait photo into a memory or a storage device of said electronic image capturing device, if said facial feature in said patch is determined to be situated at an opened state.

4. The method of claim 1, further comprising a step of capturing a current image if said facial feature does not exist in said image.

5. The method of claim 1, further comprising a step of capturing a current image, if said opened and closed state of facial feature is determined as not existing in said image.