Processing and analyzing hyper-spectral image data and information via dynamic database updating
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-017/30
G06K-009/20
출원번호
US-0280999
(2007-03-01)
등록번호
US-9002113
(2015-04-07)
국제출원번호
PCT/IL2007/000268
(2007-03-01)
§371/§102 date
20081103
(20081103)
국제공개번호
WO2007/099540
(2007-09-07)
발명자
/ 주소
Moshe, Danny S.
출원인 / 주소
Green Vision Systems Ltd.
인용정보
피인용 횟수 :
0인용 특허 :
4
초록▼
Processing and analyzing hyper-spectral image data and information via dynamic database updating. (a) processing/analyzing representations of objects within a sub set of the hyper spectral image data and information, using a first reference database of hyper spectral image data, information, and par
Processing and analyzing hyper-spectral image data and information via dynamic database updating. (a) processing/analyzing representations of objects within a sub set of the hyper spectral image data and information, using a first reference database of hyper spectral image data, information, and parameters, and, a second reference database of biological, chemical, or/and physical data, information, and parameters. Identifying objects of non-interest, and objects of potential interest, from the data/information sub-set. (b) processing/analyzing identified objects of potential interest, by further using first and second reference databases. Determining absence or presence of objects of interest, additional objects of non-interest, and non-classifiable objects of potential interest, from the data/information sub set. (c) updating first and second reference databases, using results of (a) and (b), for forming updated first and second reference databases. (d) repeating (a) through (c) for next sub-set of hyper spectral image data/information, using updated first and second reference databases. (e) repeating (d) for next sub-sets of hyper spectral image data/information.
대표청구항▼
1. A method of processing and analyzing hyper-spectral image data and information of hyperspectral imaged scenes via dynamic database updating, the method comprising the steps of: (a) identifying objects of non-interest being background of, or within, the hyperspectral imaged scenes, and objects of
1. A method of processing and analyzing hyper-spectral image data and information of hyperspectral imaged scenes via dynamic database updating, the method comprising the steps of: (a) identifying objects of non-interest being background of, or within, the hyperspectral imaged scenes, and objects of potential interest being potential targets of, or within, the hyperspectral imaged scenes, or, being potential background of, or within, the hyperspectral imaged scenes, from a sub-set of the hyper-spectral image data and information, by processing and analyzing emission type spectral representations of objects within said data and information sub-set, wherein step (a) includes using a first reference object database of hyper-spectral image data, information, and parameters of imaged reference objects, and, a second reference object database of biological, chemical, or/and physical data, information, and parameters of said imaged reference objects;(b) determining: (1) absence or presence of objects of interest, (2) additional said objects of non-interest, and (3) non-classifiable objects of potential interest, from said identified objects of potential interest, by processing and analyzing said identified objects of potential interest, wherein said determining includes performing following sub-steps (i)-(iii): (i) forming a special database of said objects of potential interest;(ii) comparing and correlating data and information of said special database of said sub-step (i) to data and information of said first reference object database of said hyper-spectral image data, information, and parameters, and, to said second reference object database of biological, chemical, or/and physical data, information, and parameters; and(iii) forming a temporary first reference object database of hyper-spectral image data, information, and parameters, and, a temporary second reference object database of biological, chemical, or/and data, information and parameters, by using results of said sub-step (ii);(c) forming an updated first reference object database and an updated second reference object database, by using results of steps (a) and (b);(d) repeating steps (a) through (c) for next sub-set of the hyper-spectral image data and information, by using said updated first reference object database and said updated second reference object database; and(e) repeating step (d) for a number of said next sub-sets of the hyper-spectral image data and information. 2. The method of claim 1, wherein step (a), said first reference object database of hyper-spectral image data, information, and parameters, includes theoretically or/and empirically determined data, information, and parameters, of, relating to, or/and associated with, spectral properties, characteristics, and behavior, of said imaged reference objects listed or indexed in a dynamically updatable reference list or index of reference objects. 3. The method of claim 2, wherein exemplary types of theoretically or/and empirically determined data, information, and parameters, are: (i) pixel intensity, (ii) signal-to-noise (S/N) ratio, (iii) image sharpness, (iv) spectral distances, and, (v) spectral fingerprint or signature pattern types of identification and characterization of said imaged reference objects listed or indexed in said dynamically updatable reference list or index of reference objects. 4. The method of claim 2, wherein step (a), said second reference object database of biological, chemical, or/and physical data, information, and parameters, includes theoretically or/and empirically determined data, information, and parameters, of, relating to, or/and associated with, biological, chemical, or/and physical properties, characteristics, and behavior, of same said imaged reference objects listed or indexed in said dynamically updatable reference list or index of reference objects. 5. The method of claim 4, wherein exemplary types of theoretically or/and empirically determined data, information, and parameters, are: (i) biological, chemical, or/and physical, composition, of said imaged reference objects listed or indexed in said dynamically updatable reference list or index of reference objects and, (ii) object morphology such as object size, shape, form, or/and configuration, of said imaged reference objects listed or indexed in said dynamically updatable reference list or index of reference objects. 6. The method of claim 1, wherein step (a), automatic pattern recognition (APR) and classification types of hyper-spectral image data and information processing and analyzing are performed by applying one or more image analysis algorithms to said sub-set of hyper-spectral image data and information. 7. The method of claim 1, wherein step (b), said sub-steps (i)-(iii) are performed for checking and controlling accuracy, precision, reproducibility, and sensitivity of performing step (a) and results formed therefrom. 8. The method of claim 1, wherein step (b), said sub-steps (i)-(iii) are performed for minimizing possible occurrence of obtaining false positive or/and false negative results in step (a). 9. The method of claim 1, further including recording, reporting, or/and displaying, progress and results while each of steps (a)-(e) is performed, during real time or/and during non-real time. 10. The method of claim 9, wherein said progress and results are with respect to the hyperspectral imaged scenes including or containing distributions of different relative numbers of said objects of non-interest, said objects of interest, and said objects of potential interest. 11. The method of claim 9, wherein said progress and results are with respect to dynamic updating of said first reference object database of hyper-spectral image data, information, and parameters, and, dynamic updating of said second reference object database of biological, chemical, or/and physical data, information, and parameters.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (4)
Slater Mark ; Herrick Robert Bruce, Hyperspectral imaging method and apparatus.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.