1. A method for restoring data stored along a data storage path of an optical storage media, said data being stored on said optical storage media and being at least in part unreadable by a conventional optical storage media reading device due to chemical or physical changes within a recording layer or a reflective layer of the optical storage media, comprising the following steps:
detecting deformations of a shape of a groove and lands of the groove extending along the data storage path, the deformations having been generated by a laser beam during a recording process of said optical storage media,
determining the data to be restored from the detected deformations and lands.
2. A method for restoring data stored along a data storage path of an optical storage media, said data storage path comprising pits and lands, said data being stored on said optical storage media and being at least in part unreadable by a conventional optical storage media reading device due to chemical or physical changes within a reflective layer of the optical storage media, the reflective layer serving for reflecting a read out laser beam, comprising the following steps:
detecting pits and lands extending along the data storage path, the pits and lands being in part unreadable by the conventional optical storage media reading device, and the pits having been generated by a stamper during a replication process, wherein the detection of the pits and lands is based upon the use of a modified optical read out means which is capable of detecting the pits and lands even if the reflective layer of said optical storage media is at least partly damaged or not present,
determining the data to be restored from the detected pits and lands.
3. The method according to claim 1 or 2, wherein a protective layer andor a reflective layer andor a recording layer of the optical storage media is removed before the deformation, pit andor land detecting step is carried out.
4. The method according to any one of claims 1 or 2, wherein, in order to detect the deformations andor pits and the lands, a scanning process is performed which scans the deformations andor the pits and lands along the data storage path and comprises the following steps:
irradiating the data storage path using a scanning laser beam,
converting the intensity of laser light reflected at the data storage path into an electronic read out signal,
extracting information related to the deformations andor to the pits and lands to be detected out of the read out signal.
5. The method according to claim 4, wherein the optical storage media is re-coated with a new recording layer andor with a new reflective layer andor at least one other new layer before the scanning process is carried out.
6. The method according to claim 5, wherein the thicknesses of said new recording layer andor of said new reflective layer andor of said other new layer are chosen such that the contrast between the deformations andor pits and the area around the deformations andor the pits is enhanced andor the slew-rate of the HF-Signal at the leading and trailing edges of the deformations andor pits is increased so that the deformations andor the pits and lands along the data storage path can be scanned by the scanning laser beam with improved precision.
7. The method according to claim 5, wherein the laser wavelength (\u03bb) andor the reading laser power andor the numerical aperture of the lens andor the rim intensities of the optical pick-up of the modified read out means is chosen such that the contrast between the deformations andor pits and the area around the deformations andor the pits is enhanced andor the slew-rate of the HF-Signal at the leading and trailing edges of the deformations andor pits is increased so that that the deformations andor the pits and lands andor the area around pits and lands can be scanned by the scanning laser beam with improved precision.
8. The method according to claim 7, wherein the laser wavelength (\u03bb) used by the optical pick-up is higher or lower than the standard laser wavelength according to the specification of the optical storage media.
9. The method according to claim 7, wherein the reading laser power used by the optical pick-up is higher or lower than the standard laser power according to the specification for normal data read-out from the optical storage media.
10. The method according to claim 7, wherein the numerical aperture of the lens of optical pick-up is larger or smaller than the standard numerical aperture according to the specification of the optical storage media.
11. The method according to claim 7, wherein the radial andor the tangential rim intensity of the optical pick-up is larger or smaller than the standard radial or tangential rim intensity according to the specification for normal data read-out from the optical storage media.
12. The method according to claim 4, wherein the scanning laser beam irradiates the data storage path from the normal read-out face or from the opposite face of the optical storage media.
13. The method according to claim 5, wherein the read out signal is subjected to signal processing.
14. The method according to claim 13, wherein the signal processing comprises additional filter processing andor edge detection processing in order to improve the quality of the deformation detecting step andor pit detecting step and land detecting step.
15. The method according to claim 14, wherein, in order to determine the data to be restored from the detected deformations andor from the detected pits and lands an assignment step is performed, which assigns each detected deformation andor pit and land to a specific standard effect length.
16. The method according to claim 15, wherein the signal processing comprises steps to remove andor correct pulse lengths which are shorter than a first predetermined value and longer than a second predetermined value resulting from the detected deformations andor from the detected pits and lands after an auto-slicer has generated a digital signal with leading and trailing edges corresponding to the positions of the detected deformations andor of the detected pits and the lands at a certain decision level of the high frequency (HF) signal.
17. The method according to claim 15, wherein the assignment step is based upon statistical signal processing.
18. The method according to claim 17, wherein the assignment step comprises the steps of:
processing at least a part of the read out signal in order to measure the pulse lengths of several deformations andor of several pits and lands,
calculating a deformationpit histogram and a land histogram from the measured pulse lengths,
assigning each of the peaks of the calculated histograms to a specific effect length,
calculating the time difference between each of the peaks of the histograms and the corresponding standard effect length,
correcting each pulse length belonging to a specific peak of the histograms by subtracting or adding the corresponding calculated time difference.
19. The method according to claim 17, wherein the assignment step comprises the steps of:
processing at least a part of the read out signal in order to measure the pulse lengths of several deformations andor of several pits and lands,
calculating modified deformationpit histograms and modified land histograms from the measured pulse lengths by sorting the pulse length measurements depending on what type of symbols have occurred before andor after the pulse length measurements
assigning each of the peaks of the modified histograms to a specific effect length,
calculating the time difference between each of the peaks of the modified histograms and the corresponding standard effect length,
correcting the pulse length belonging to a specific peak of the modified histograms by subtracting or adding the corresponding calculated time difference based on these modified histograms.
20. Optical storage media reading device for restoring data stored along a data storage path of an optical storage media, said data being stored on said optical storage media and being at least in part unreadable by a conventional optical storage media reading device due to chemical changes or physical changes within a recording layer andor a reflective layer of the optical storage media, comprising:
optical read out means adapted for irradiating the optical storage media along the data storage path with a read out laser beam and converting the intensity of laser light reflected at the data storage path into a electronic read out signal, wherein said optical read out means is adapted for detecting deformations of a shape of a groove extending along the data storage path even if the reflective layer andor the recording layer of said optical storage media is at least partly damaged or not present, said deformations having been generated by a laser beam during a recording process of said optical storage media,
extracting means adapted for extracting information out of the read out signal relating to the deformations and lands,
processing means adapted for processing the extracted information in order to obtain the data to be restored.
21. Optical storage media reading device for restoring data stored along a data storage path of an optical storage media, said data being stored on said optical storage media and being at least in part unreadable by a conventional optical storage media reading device due to chemical changes or physical changes within a reflective layer of the optical storage media, the reflective layer serving for reflecting a read out laser beam, comprising:
optical read out means adapted for irradiating the optical storage media along the data storage path with a read out laser beam and converting the intensity of laser light reflected at the data storage path into an electronic read out signal, wherein said optical read out means is adapted for detecting pits and lands extending along the data storage path, the pits and lands being in part unreadable by the conventional optical storage media reading device, and pits and lands having been generated by a stamper during a replication process even if the reflective layer of said optical storage media is at least partly damaged or not present,
extracting means adapted for extracting information out of the read out signal relating to said pits and lands,
processing means adapted for processing the extracted information in order to obtain the data to be restored.
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. (canceled)
2. (canceled)
3. (canceled)
4. (canceled)
5. (canceled)
6. (canceled)
7. (canceled)
8. (canceled)
9. A computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, which when executed causes a computer to implement the method comprising:
pre-processing a coronary angiography sequence of images, the images depicted in an image frame, including:
detecting and labeling regions of interest in at least a subset of images of the sequence, wherein the region of interest contain a coronary vessel;
estimating shape and motion in at least the subset of images of the image sequence, including extracting centerline curves of coronary vessels and computing optical flow within an angiogram sequence;
sampling the extracted centerline curves to generate feature points;
sampling a surrounding region of the generated feature points to capture shape and motion context of a depicted vessel; and
forming a feature set for classification of the depicted vessel, wherein features of the represented vessels are constructed from pyramid histograms of shape and motion context;
determining a set of characteristics separating data in feature space, where the feature set is derived from pyramid histograms of the samplings, and the training employs angiogram sequences with known viewpoint labels; and
returning a classification result for a new sequence of images based on a recognized shape and motion of the vessel, including fitting the multiclass support vector machine to computed features and determining where a vessel feature lies in the feature space against a classification boundary.
10. The computer program product of claim 9, further comprising computer readable program code configured to use recognition stage processing, including computer readable program code which generates a final pyramid histogram feature vector from shape and motion context and classifies the sequence using the computed feature vector.
11. The computer program product of claim 9, further comprising program code configured to detect regions of interest including computer readable program code configured to estimate and remove a border associated with the image.
12. The computer program product of claim 9, wherein the program code configured to sample the surrounding region includes program code which when executed causes a computer to implement the method comprising:
capturing a local shape of the vessel through a modified shape context;
capturing motion context of the vessel at each point of the vessel shape, including capturing motion as a vector with respect to the concatenated regions; and
building a first pyramid histogram representation of a shape of the vessel shape and a second pyramid histogram representation of motion of the vessel.
13. The computer program product of claim 12, further comprising program code configured to combine the first and second histograms, including program code configured to concatenate the first and second histograms at each point and form a concatenated vector as a feature vector defining each keypoint.
14. The computer program product of claim 13, further comprising program code configured to form a matrix from combined shape and motion vectors, wherein each row in the matrix corresponds to features at each keypoint and each column represents one dimension of the shape context or one dimension of the motion context.
15. The computer program product of claim 9, further comprising program code configured to extract salient features that characterize the appearance of coronary arteries under different viewpoints, wherein the extracted features include prior labeled training sequences and a new sequence.
16. A system comprising:
a processor in communication with memory and a storage device, the storage device to store angiographic image sequence data;
a functional unit in communication with the memory and comprising tools which when executed by the processor classify vessels in the image sequence data, the tools comprising:
a pre-processing image manager to pre-process a coronary angiography sequence of images, including extraction of salient features that characterize appearance of coronary arteries under different viewpoints, the pre-processing image manager to:
detect and label regions of interest in at least a subset of images of the sequence;
estimate shape and motion in at least the subset of images, including extraction of centerline curves of coronary vessels and computation of optical flow within an angiogram sequence;
sample the extracted centerline curves to generate feature points;
sample a surrounding region of the generated feature points to capture shape and motion context of the depicted vessel; and
form one or more feature sets for classification of vessels based on the captured shape and motion context;
a training vector manager in communication with the pre-processor image manager, the vector manager to train a multiclass support vector machine to determine a set of characteristics separating data in feature space, the training vector manager to derive a feature set from pyramid histograms of the samplings, and employ angiogram sequences with known viewpoint labels; and
a director in communication with the vector manager, the director to return a classification result for a new sequence of images based on the recognized shape and motion of the vessel, including fitting the multiclass support vector machine to computed features.
17. The system of claim 16, further comprising the pre-processing image manager to employ recognition stage processing, including generation of a final pyramid histogram feature vector from shape and motion context and classification of the sequence using the computed feature vector.
18. The system of claim 16, wherein the pre-processing image manager estimates and removes a border associated with the image when detecting regions of interest.
19. The system of claim 16, further comprising the pre-processing image manager, when sampling the surrounding region to:
capture a local shape of the vessel through a modified shape context;
capture motion context of the vessel at each point of the vessel shape, wherein the captured motion is represented as a vector with respect to the concatenated regions; and
build a first pyramid histogram representation of a shape of the vessel shape and a second pyramid histogram representation of motion of the vessel.
20. The system of claim 19, further comprising the pre-processing image manager to combine the first and second histograms, including concatenation of the first and second histograms at each point and formation of a concatenated vector as a feature vector defining each keypoint.
21. The system of claim 20, further comprising the director to form a matrix from combined shape and motion vectors, the director to allocate each row in the matrix to correspond to features at each keypoint, and each column to represent one dimension of the shape context or one dimension of the motion context.
22. The system of claim 16, further comprising the pre-processing image manager to extract salient features that characterize the appearance of coronary arteries under different viewpoints, wherein the extracted features include prior labeled training sequences and a new sequence.
23. The method of claim 1, wherein the feature set for classification of the depicted vessel includes a vector, and a set of characteristics separating data in feature space includes hyper planes.
24. The computer program product of claim 9, wherein the feature set for classification of the depicted vessel includes a vector, and a set of characteristics separating data in feature space includes hyper planes.
25. The system of claim 16, wherein the feature set for classification of the depicted vessel includes a vector, and a set of characteristics separating data in feature space includes hyper planes.