Cumulative image recognition method and application program for the same

• US 9,317,535 B2
• Filed: 12/16/2013
• Issued: 04/19/2016
• Est. Priority Date: 12/16/2013
• Status: Expired due to Fees

• Current Assignee: Viscovery Pte. Ltd.
• Original Assignee: Viscovery Pte. Ltd.
• Inventors: Huang, Chun-Chieh, Lin, Hsin-Yu
• Primary Examiner(s): Chawan, Sheela C
• Application Number:
  US14/107,445
• Publication Number:
  US 20150170003A1
• Time in Patent Office: 855 Days
• Field of Search: 382/181, 382/187, 382/218, 382/209, 382/217, 704/200, 704/231, 704/251, 704/236, 704/239, 704/254, 704/270, 704/275, 704/252, 704/241, 704/238
• US Class Current: 1/1
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 18/25 Fusion techniques
• CPC Class Codes: G06V 10/80 Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level multimodal speaker identification or verification G10L17/10
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments

Abstract

A cumulative image recognition method performs a matching analysis on frame and matching data in a mobile device when the mobile device focuses on a recognition target and captures frame of the image of the recognition target. The method obtains the feature value of each matching data according to the matching result, and determines if one of the matching data has an optimal result matching the recognition target according to several entries of feature values. If no optimal result, then the method respectively sums up the feature value of each matching data into a summing feature value and determines if the plurality of the matching data has a candidate result similar to the recognition target according to several entries of the summing feature values. If no candidate result, the mobile device captures the next frame on the recognition target, and performs next matching analysis on the next frame.

Claims

1. A cumulative image recognition method for a mobile device, wherein a plurality of the matching data is saved in the mobile device, the cumulative image recognition method comprising:

a) capturing frames of a recognition target via an image capturing unit of a mobile device;

b) performing with the mobile device matching analysis on the frame and the plurality of the matching data;

c) respectively obtaining with the mobile device feature values of each matching data according to the analysis result;

d) determining with the mobile device if the feature value of the matching data is higher than a first threshold value;

e) the matching data being an optimal result if the matching data has the feature value higher than the first threshold value, and displaying the optimal result on a display monitor of the mobile device;

f) if the feature value of the matching data is not higher than the first threshold value, writing with the mobile device the feature value of each matching data in an similar list for summing up the summing feature value of each matching data written in the similar list;

g) determining with the mobile device if the summing feature value of the matching data is higher than a second threshold value;

h) if the summing feature value of the matching data is not higher than the second threshold value, re-executing step a to step g; and

i) the matching data being a candidate result if the matching data has the summing feature value higher than the second threshold value, and displaying the candidate result on the display monitor of the mobile device.

2. The cumulative image recognition method of claim 1, wherein the mobile device executes an image analysis via an application program stored on a non-transitory computer readable medium in the mobile device, for respectively acquiring one or several featuring points identical between each matching data and the frame, the feature value is the quantity of the one or several featuring points.

3. The cumulative image recognition method of claim 2, wherein the second threshold value is higher than the first threshold value.

4. The cumulative image recognition method of claim 2, wherein the step a comprising following steps:

a1) initiating the application program controlling the image capturing unit to enter into a camera capturing model;

a2) the image capturing unit scanning the external image for determining if the mobile device moves via scanning the external image the image capturing unit;

a3) if the mobile device does not move, the image capturing unit capturing the frame.

5. The cumulative image recognition method of claim 4, wherein the method further comprises a step a4:

following step a3, if the mobile device moves, and the move value exceeds a predetermined threshold value, clearing the summing feature values written in the similar list.

6. The cumulative image recognition method of claim 2, wherein further comprises a step j:

after step e and step h, clearing the summing feature values written in the similar list.

7. The cumulative image recognition method of claim 2, wherein further comprising following steps:

k) following step c, establishing a result list according to the feature value of each matching data;

l) determining if the feature values in the result list are all zero or all less than a third threshold value;

m) if the feature values in the result list are all zero or all less than a third threshold value, clearing the summing feature values written in the similar list; and

n) if the feature values in the result list are not all zero or all less than a third threshold value, continuing to execute step d.

8. The cumulative image recognition method of claim 7, wherein the step m comprising following steps:

m1) if the feature values in the result list are all zero or all less than a third threshold value, re-executing step a, b, c, k and l;

m2) following step m1, if the feature values in the result list still are all zero or all less than a third threshold value, clearing the summing feature values written in the similar list.

9. The cumulative image recognition method of claim 7, wherein further comprises a step o:

after step e, h, m, deleting the result list.

10. The cumulative image recognition method of claim 2, wherein in step f, the mobile device only sums up the feature value high than a third threshold value with the similar list, wherein the third threshold value is less than the first threshold value and the second threshold value.