1. A method of inhibiting angiogenesis in undesired tissue in a subject consisting of administering to the subject an effective amount of itraconazole.
2. The method of claim 1, wherein the compound is administered for treatment of retinoblastoma, cystoid macular edema (CME), exudative age-related macular degeneration (AMD), diabetic retinopathy, diabetic macular edema, or ocular inflammatory disorders.
3. The method of claim 1, wherein the undesired tissue is a tumor.
4. The method of claim 1, wherein the undesired tissue is dermis; epidermis; endometrium; a surgical wound; or disorder or disease of the retina, gastrointestinal tract, umbilical cord, liver, kidney, reproductive system, lymphoid system, central nervous system, breast tissue, urinary tract, circulatory system, bone, muscle, or respiratory tract.
5. The method of claim 1, wherein the undesired tissue is adipose tissue.
6. A method of inhibiting or reducing undesired angiogenesis in a subject consisting of administering to the subject an angiogenesis-inhibiting effective amount of itraconazole.
7. The method of claim 6, wherein the compound is administered in an amount effective for treatment of retinoblastoma, cystoid macular edema (CME), exudative age-related macular degeneration (AMD), diabetic retinopathy, diabetic macular edema, or ocular inflammatory disorders.
8. The method of claim 6, wherein the undesired angiogenesis is in a tumor.
9. The method of claim 6, wherein the undesired angiogenesis is in a tissue selected from dermis; epidermis; endometrium; and a surgical wound; or disorder or disease of the retina, gastrointestinal tract, umbilical cord, liver, kidney, reproductive system, lymphoid system, central nervous system, breast tissue, urinary tract, circulatory system, bone, muscle, or respiratory tract.
10. The method of claim 1 or 6, wherein the undesired tissue or angiogenesis, respectively, is associated with cancer in the subject.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method comprising the steps of:
determining a first list of possible word transcriptions of a handwritten word;
determining, from a plurality of additional lists of possible word transcriptions of handwritten words, at least one second list; and
determining which word from the first list or at least one second list should be selected as a best text word transcription of the handwritten word.
2. The method of claim 1, wherein the best text word transcription of the handwritten word is an incorrect transcription of the handwritten word
3. The method of claim 1, wherein the best text word transcription of the handwritten word is a correct transcription of the handwritten word.
4. The method of claim 1, wherein the step of determining at least one second list comprises the step of determining a metric between the first list and each of the additional lists.
5. The method of claim 4, wherein the first and each additional list comprise a plurality of scores, wherein the metric comprises a correlation factor.
6. The method of claim 1, wherein the step of determining which word from the first list or at least one second list should be selected as a best text word transcription of the handwritten word comprises the steps of:
providing a feature of the first and additional lists; and
using the feature to select a best text word from the first and at least one additional lists.
7. The method of claim 6, wherein the step of using the feature to select a best text word from the first and at least one additional lists further comprising the step of selecting the best text word according to at least one combination rule, the at least one combination rule using each of the at least one features.
8. The method of claim 7, wherein the at least one combination rule further comprises a decision tree of rules.
9. A method comprising the steps of:
using a base classifier to determine a first list comprising a plurality of text words, each text word being a possible transcription of a handwritten word; and
combining the base classifier with a nearest neighbor classifier to determine a resultant text word, the nearest neighbor classifier comprising a plurality of additional lists, each list comprising a plurality of words.
10. A method comprising the steps of:
using a base classifier to determine a first list comprising a plurality of text words, each text word being a possible transcription of a handwritten word;
determining a plurality of lists in a nearest neighbor classifier, each of the lists comprising a plurality of text words;
providing a plurality of features of a list;
selecting at least one nearest neighbor list, from the nearest neighbor classifier; by determining correlations between the first list and the lists in the nearest neighbor classifier; and
determining, by using the features, which text word of the first and at least one neatest neighbor list should be selected as a best choice of a translation of the handwritten word.
11. A computer system comprising:
a memory that stores computer-readable code; and
a processor operatively coupled to the memory, the processor configured to implement the computer-readable code, the computer-readable code configured to:
use a base classifier to determine a first list comprising a plurality of text words, each text word being a possible transcription of a handwritten word;
determine a plurality of lists in a nearest neighbor classifier, each of the lists comprising a plurality of text words;
provide a plurality of features of a list;
select at least one nearest neighbor list, from the nearest neighbor classifier; by determining correlations between the first list and the lists in the nearest neighbor classifier; and
determine, by using the features, which text word of the first and at least one nearest neighbor list should be selected as a best choice of a translation of the handwritten word.
12. An article of manufacture comprising:
a computer readable medium having computer-readable code means embodied thereon, the computer-readable program code means comprising:
a step to use a base classifier to determine a first list comprising a plurality of text words, each text word being a possible transcription of a handwritten word;
a step to determine a plurality of lists in a nearest neighbor classifier, each of the lists comprising a plurality of text words;
a step to provide a plurality of features of a list;
a step to select at least one nearest neighbor list, from the nearest neighbor classifier, by determining correlations between the first list and the lists in the nearest neighbor classifier; and
a step to determine, by using the features, which text word of the first and at least one nearest neighbor list should be selected as a best choice of a translation of the handwritten word.