US5754676A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image classification apparatus
Assignee: Olympus Corp
•
Filing: 1995-04-07
•
Granted: 1998-05-19
•
Expires: 2015-04-07
Abstract
Abstract An image classification apparatus includes an image input device for inputting image data. A filing device stores the input image data and performs a read, retrieval, or edit operation on the data in accordance with a predetermined instruction. A normalizing unit corrects variations in various image input conditions or variations in image input devices to make the input conditions in execution agree with those in learning. A feature extracting unit extracts a feature amount effective for classification. A classification determination unit performs a classification determination operation on the basis of the feature amount obtained by the feature extracting unit. A display unit synthesizes a result of the classification determination operation with the input image, and displays the synthesized result. A learning control unit controls the feature extracting unit and the classification determination unit on the basis of the predetermined learning data. Accordingly, the classification apparatus classifies a portion of the input image which is difficult to extract by binarization or three-dimensional display alone, and displays the classified portion in an easily recognizable visual form.
Inventors
- 👤 Yasuhiro Komiya
- 👤 Tatsuo Nagasaki
- 👤 Xiaohui Kimura
- 👤 Toshiaki Wada
- 👤 Koichi Ito
- 👤 Yoshinobu Omata
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 14:20
CPC Classifications
G; G06; G06F; G06F18/00; G06F18/20; G06F18/21
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
276 words
An image classification apparatus comprising: an information input device for inputting information to be classified; feature extracting means for extracting feature information from the input information; and classification determining means for determining a type of the input information on the basis of at least the feature information extracted by said feature extracting means, and for classifying the input information in accordance with the determined type; said feature extracting means including: multivariate analyzing means for converting the input information into information suitable for classification performed by said classification determining means; differential statistic detecting means for calculating a feature of the input information by obtaining a probability Pδ(k) (k=0, 1, . . . , n-1) with which a density difference between two points separated by a fixed displacement δ=(r,e) in an image frame region of interest in at least one image frame of the input information is k, and for determining a type of an object in the at least one image frame region in accordance with the calculated feature; run-length matrix detecting means for producing a run-length matrix which characterizes the object in the at least one image frame region and which has as elements frequencies Pθ(i,j) (i=1, 2, . . . , n-1, j=1, 2, . . . , L) at which points having a density corresponding to an angle θ succeed in the at least one image frame region, said run-length matrix detecting means calculating a feature amount from the run-length matrix and representing a specific speckle pattern using the calculated feature amount; and pre-processing means for causing the feature amount to be calculated prior to providing the input information to said multivariate analyzing means.
Claim 2
Dependent Claim
276 words
An image classification apparatus comprising: an information input device for inputting information to be classified; feature extracting means for extracting feature information from the input information; and classification determining means for determining a type of the input information on the basis of at least the feature information extracted by said feature extracting means, and for classifying the input information in accordance with the determined type; said feature extracting means including: multivariate analyzing means for converting the input information into information suitable for classification performed by said classification determining means; differential statistic detecting means for calculating a feature of the input information by obtaining a probability Pδ(k) (k=0, 1, . . . , n-1) with which a density difference between two points separated by a fixed displacement δ=(r,e) in an image frame region of interest in at least one image frame of the input information is k, and for determining a type of an object in the at least one image frame region in accordance with the calculated feature; run-length matrix detecting means for producing a run-length matrix which characterizes the object in the at least one image frame region and which has as elements frequencies Pθ(i,j) (i=1, 2, . . . , n-1, j=1, 2, . . . , L) at which points having a density corresponding to an angle θ succeed in the at least one image frame region, said run-length matrix detecting means calculating a feature amount from the run-length matrix and representing a specific speckle pattern using the calculated feature amount; and pre-processing means for causing the feature amount to be calculated prior to providing the input information to said multivariate analyzing means.
Claim 3
Dependent Claim
190 words
An image classification apparatus comprising: an information input device for inputting information to be classified; feature extracting means for extracting feature information from the input information; classification determining means for determining a type of the input information on the basis of at least the feature information extracted by said feature extracting means, and for classifying the input information in accordance with the determined type; and learning means for constructing at least one of said feature extracting means and said classification determining means; said feature extracting means including multivariate analyzing means for converting the input information into information suitable for classification performed by said classification determining means, and pre-processing means for calculating a feature amount prior to providing the input information to said multivariate analyzing means, and said learning means including: a teaching data input device for enabling teaching data required to perform learning to be input, classification vector calculating means for performing calculations for setting various conditions in said feature amount extracting means on the basis of the input teaching data, and learning control means for controlling operation of said teaching data input device and said classification vector calculating means.
Claim 4
Dependent Claim
190 words
An image classification apparatus comprising: an information input device for inputting information to be classified; feature extracting means for extracting feature information from the input information; classification determining means for determining a type of the input information on the basis of at least the feature information extracted by said feature extracting means, and for classifying the input information in accordance with the determined type; and learning means for constructing at least one of said feature extracting means and said classification determining means; said feature extracting means including multivariate analyzing means for converting the input information into information suitable for classification performed by said classification determining means, and pre-processing means for calculating a feature amount prior to providing the input information to said multivariate analyzing means, and said learning means including: a teaching data input device for enabling teaching data required to perform learning to be input, classification vector calculating means for performing calculations for setting various conditions in said feature amount extracting means on the basis of the input teaching data, and learning control means for controlling operation of said teaching data input device and said classification vector calculating means.
Claim 5
Dependent Claim
38 words
The image classification apparatus according to claim 2, further comprising at least one of: normalizing means for normalizing the input information; and display means for displaying the type of the input information determined by said classification determining means.
Claim 6
Dependent Claim
31 words
The image classification apparatus according to claim 2, wherein said information input device comprises at least one of an image input device, a filing device, and a general information input device.
Claim 7
Dependent Claim
39 words
The image classification apparatus according to claim 3, wherein said normalizing means includes at least one normalizing unit for performing normalization in accordance with predetermined set conditions, and normalization control means for controlling said at least one normalization unit.
Claim 8
Dependent Claim
21 words
The image classification apparatus according to claim 3, wherein said normalizing means includes setting means for setting desired conditions for normalization.
Claim 9
Dependent Claim
37 words
The image classification apparatus according to claim 3, wherein said normalizing means includes means for outputting control information for selecting a processing operation of at least one of said feature extracting means and said classification determining means.
Claim 10
Dependent Claim
73 words
The image classification apparatus according to claim 2, wherein said pre-processing means includes rough pattern detecting means for extracting, from at least one image frame region of the input information, a feature amount of a first region larger than said at least one image frame region, and fine pattern detecting means for extracting, from said at least one image frame region, a feature amount of a second region smaller than said first region.
Claim 11
Dependent Claim
87 words
The image classification apparatus according to claim 2, wherein said classification determining means comprises at least one of: fuzzy determining means for converting the input information into a form suitable for logical determination; logical determining means for logically determining one of an output from said fuzzy determining means and the input information; and feedback means for selecting, on the basis of an output from said logical determining means, one of a processing operation of said feedback means and a preceding processing operation of said logical determining means.
Claim 12
Dependent Claim
56 words
The image classification apparatus according to claim 3, wherein said display means includes display image generating means for displaying an image of the input information, and one of information relating to the feature information extracted by said feature extracting means and information relating to the type of the input information determined by said classification determining means.
Claim 13
Dependent Claim
49 words
The image classification apparatus according to claim 10, wherein said display image generating means displays the image in a predetermined visual form in accordance with one of the feature information extracted by said feature extracting means and the type of the input information determined by said classification determining means.
Claim 14
Dependent Claim
48 words
The image classification apparatus according to claim 11, wherein said display image generating means displays the image in a particular color in accordance with one of the feature information extracted by said feature extracting means and the type of the input information determined by said classification determining means.
Claim 15
Dependent Claim
47 words
The image classification apparatus according to claim 11, wherein said display image generating means displays the image in graphical form in accordance with one of the feature information extracted by said feature extracting means and the type of the input information determined by said classification determining means.
Claim 16
Dependent Claim
35 words
The image classification apparatus according to claim 2, wherein said learning control means includes means for controlling a display operation of said input teaching data on a monitor for displaying images of the input information.
Claim 17
Dependent Claim
25 words
The image classification apparatus according to claim 2, wherein said classification vector calculating means includes means for calculating a classification vector using a statistical method.
Claim 18
Dependent Claim
38 words
The image classification apparatus according to claim 2, wherein said learning control means includes means for outputting control information for selecting a processing operation of at least one of said feature extracting means and said classification determining means.
Claim 19
Dependent Claim
107 words
The image classification apparatus according to claim 3, wherein said normalizing means comprises: density histogram calculating means for calculating a histogram pertaining to a density of an entire image of the input information; binarizing means for binarizing said entire image in accordance with said calculated histogram and for dividing said entire image into regions on the basis of a numerical value obtained from said binarizing; contour line extracting means for extracting a contour line of an object from each of the regions divided by said binarizing means; and line segment detecting means for detecting a straight-line component of the object extracted by the contour line extracting means.
Claim 20
Dependent Claim
136 words
An image classification apparatus according to claim 2, wherein: said information input device includes coordinate designating means for sequentially designating processing regions to be classified from a region of interest of an image of the input information; and said classification determining means includes: fuzzy determining means having a neural network for converting the input information into a form suitable for logical determination; and logical determining means comprising binarizing means for binarizing a plurality of outputs from said neural network of said fuzzy determining means, cumulative adding means for cumulatively adding binarization results, maximum value detecting means for calculating a maximum value of the cumulatively added binarization results in all of the processing regions designated by said coordinate designating means, and final determining means for classifying the region of interest in accordance with the calculated maximum value.
Claim 21
Dependent Claim
92 words
The image classification apparatus according to claim 2, wherein: said learning means includes: additional teaching data buffer means for sequentially generating and storing additional teaching data corresponding to feature amounts of information supplied from said feature extracting means; and buffer control means for inputting new teaching data to said teaching data input device based on the feature amounts, said new teaching data being stored in said additional teaching data buffer means; and said classification vector calculating means performs said calculations on the basis of said teaching data and said additional teaching data.
Claim 22
Dependent Claim
214 words
An image classification apparatus comprising; an information input device for inputting information to be classified; normalizing means for normalizing the input information; feature extracting means for extracting feature information from the input information; and classification determining means for determining a type of the input information on the basis of at least the feature information extracted by said feature extracting means, and for classifying the input information in accordance with the determined type; said feature extracting means including multivariate analyzing means for converting the input information into information suitable for classification performed by said classification determining means, and pre-processing means for calculating a feature amount prior to providing the input information to said multivariate analyzing means; and said normalizing means including: density histogram calculating means for calculating a histogram pertaining to a density of an entire image of the input information, binarizing means for binarizing said entire image in accordance with said calculated histogram and for dividing said entire image into regions on the basis of a numerical value obtained from said binarizing, contour line extracting means for extracting a contour line of an object from each of the regions divided by said binarizing means, and line segment detecting means for detecting a straight-line component of the object extracted by the contour line extracting means.
Claim 23
Dependent Claim
214 words
An image classification apparatus comprising; an information input device for inputting information to be classified; normalizing means for normalizing the input information; feature extracting means for extracting feature information from the input information; and classification determining means for determining a type of the input information on the basis of at least the feature information extracted by said feature extracting means, and for classifying the input information in accordance with the determined type; said feature extracting means including multivariate analyzing means for converting the input information into information suitable for classification performed by said classification determining means, and pre-processing means for calculating a feature amount prior to providing the input information to said multivariate analyzing means; and said normalizing means including: density histogram calculating means for calculating a histogram pertaining to a density of an entire image of the input information, binarizing means for binarizing said entire image in accordance with said calculated histogram and for dividing said entire image into regions on the basis of a numerical value obtained from said binarizing, contour line extracting means for extracting a contour line of an object from each of the regions divided by said binarizing means, and line segment detecting means for detecting a straight-line component of the object extracted by the contour line extracting means.
References Cited (Backward Citations)
US5031228A
Cited
US5465308A
Cited
US5239594A
Cited
US5343390A
Cited
US5319549A
Cited
US5497430A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-05-18 | 2001-11-17 | 2002-05-19 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-05-18 | 2005-11-17 | 2006-05-19 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-05-18 | 2009-11-17 | 2010-05-19 | $7700.00 | Window Closed / Lapsed |