1. An image projecting apparatus forming an image by projecting a light irradiated from a light source onto a digital micromirror panel, comprising:
the digital micromirror panel configured such that a normal plane of a movable mirror surface of the digital micromirror panel, which is parallel with a longer side of the movable mirror surface, is parallel with an optical axis of the light source;
a first reflective mirror configured to reflect the light from the light source at a predetermined angle; and
a second reflective mirror configured to receive the light reflected from the first reflective mirror and to reflect the light onto the movable mirror surface of the digital micromirror panel,
wherein the second reflective mirror is configured such that the light from the first reflective mirror is reflected from the second reflective mirror to be incident on the movable mirror surface of the digital micromirror panel, with an angle between the normal plane of the movable surface and the incident light being 1.5\u02dc2.5 times greater than the angle at which the digital micromirror is tilted, and also with an angle between the orthographic projective line of the incident light and the longer side of the movable mirror surface being 40\xb0-50\xb0.
2. The image projecting apparatus of claim 1, further comprising a first lens group provided with at least one lens, having a positive refractivity, and disposed on the optical path between the light source and the first reflective mirror; and
a second lens group provided with at least one lens, having a positive refractivity, and disposed on the optical path between the second reflective mirror and the digital micromirror panel.
3. The image projecting apparatus of claim 2, further comprising a third lens group provided with at least one lens, having a positive refractivity, and disposed on the optical path between the first reflective mirror and the second reflective mirror.
4. The image projecting apparatus of claim 1, further comprising a prism system, wherein the light reflected onto the movable mirror surface of the digital micromirror panel by the second reflective mirror is also reflected by the prism.
5. The image projecting apparatus of claim 4, wherein the prism is a total internal reflection prism.
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 for partitioning a first plurality of objects and a second plurality of objects, each of the first plurality of objects being related to at least one of the second plurality of objects according to at least one characteristic of each object, the method being performed by a data processor, the method comprising:
partitioning the first plurality of objects into a first plurality of object subsets according to a subset of the second plurality of objects; and
partitioning the second plurality of objects according to a subset of the first plurality of objects to form a second plurality of object subsets, such that said partitioning of the second plurality of objects is coupled to said partitioning of the first plurality of objects and wherein said first and second plurality of objects are partitioned in an unsupervised manner.
2. The method of claim 1, wherein a subset of the first plurality of objects comprises the entirety of the first plurality of objects.
3. The method according to claim 1, wherein said partitioning of the first plurality of objects comprising:
applying a clustering algorithm on the first plurality of objects according to said at least one characteristic to form a plurality of object subsets; and
detecting at least one stable cluster from said plurality of object subsets.
4. The method of claim 3, wherein said clustering algorithm is the superparamagnetic clustering algorithm.
5. The method of any of claim 1, wherein the method is repeated until no additional subgroups are detected.
6. The method of claim 5, wherein no additional subgroups are detected for both the first plurality of objects and the second plurality of objects.
7. The method of claim 1, wherein said partitioning of the first plurality of objects is performed by partitioning a plurality of subset groups of the first plurality of objects according to a known classification.
8. The method of claim 1, further comprising:
analyzing each group of said at least two groups of the second plurality of objects by comparing said group of said at least two groups of the second plurality of objects to an entirety of the second plurality of objects to determine if said group is differentiated from the second plurality of objects.
9. The method of claim 1, further comprising:
analyzing each subset of the first plurality of objects by comparing said subset of the first plurality of objects to an entirety of the first plurality of objects to determine if said subset is differentiated from the first plurality of objects.
10. The method of claim 8, wherein the analysis is performed according to a statistical test for similarity.
11. The method of any of claim 8, wherein the first plurality of objects is normalized before being portioned.
12. The method of any of claim 8, wherein the second plurality of objects is normalized before being partitioned.
13. The method of any of claim 1, wherein the first plurality of objects are genes and the second plurality of objects are samples for being analyzed according to a characteristic of said genes.
14. The method of claim 13, wherein said samples are characterized according to expression levels of said genes.
15. The method of claim 13, wherein said genes forming a cluster characterize a pathological state of a plurality of subjects, said samples being obtained from said plurality of subjects.
16. The method of any of claim 13, wherein said genes forming a cluster participate together in a biological process.
17. The method of any of claim 13, wherein said genes are characteristic of samples taken from subjects having a cancerous condition.
18. The method of claim 17, wherein at least one characteristic of said genes partitions said samples according to a type of cancer in said cancerous condition.
19. The method of claim 18, wherein said at least one characteristic of said genes is an expression profile of said genes.
20. The method of claim 19, wherein said expression profile is determined as an expression matrix, such that the division of said samples into subgroups according to said expression profile for said genes is performed with said expression matrix.
21. The method of claim 18, wherein said at least one characteristic of said genes is an effect of treatment on said subjects.
22. A method for separating at least one of a first plurality of objects and a second plurality of objects into at least two groups, each of the first plurality of objects being related to at least one of the second plurality of objects, the method being performed by a data processor, the method comprising: dividing the first plurality of objects into a first plurality of object subsets; and partitioning the second plurality of objects according to at least one of said first plurality of object subsets to form at least two groups of the second plurality of objects, wherein the first plurality of objects are keywords and the second plurality of objects arc documents containing said keywords.
23. The method of claim 1, wherein a natural separation exists within at least one of the first plurality of objects and of the second plurality of objects.
24. A method for selecting a second plurality of objects according to a first plurality of objects, each of the first plurality of objects being related to at least one of the second plurality of objects according to at least one characteristic of each object, the method being performed by a data processor, the method comprising:
partitioning the first plurality of objects into a plurality of first object subsets according to at least one characteristic of the first plurality of objects;
partitioning the second plurality of objects according to each one of said plurality of first object subsets to form a subgroup of the second plurality of objects according to each one of said plurality of first object subsets; and
comparing each subgroup of the second plurality of objects to every other subgroup of the second plurality of objects, such that said partitioning of the second plurality of objects is coupled to said partitioning of the first plurality of objects.
25. A method for selecting a second plurality of biological objects from a collection of biological objects according to a first plurality of biological objects, each of the first plurality of objects being related to at least one of the second plurality of objects according to at least one characteristic of each object, wherein the relationship is known from data about the objects, the method being performed by a data processor, the method comprising:
partitioning the first plurality of objects into a plurality of first object subsets according to at least one characteristic of the first plurality of objects;
selecting the second plurality of objects according to each one of said plurality of first object subsets from the collection of objects; and
comparing the second plurality of objects to every other subgroup of the collection of objects, such that said selecting of the second plurality of objects is coupled to said partitioning of the first plurality of objects in an unsupervised manner.
26. The method of claim 25, wherein said partitioning and said selecting are performed repeatedly until no additional stable partitions are obtained for at least one of said first or said second plurality of objects.
27. The method of claim 1, wherein a subset of the second plurality of objects comprises the entirety of the second plurality of objects.