Computer vision systems and methods for unsupervised learning for progressively aligning noisy contours
Computer vision systems and methods for noisy contour alignment are provided. The system generates a loss function and trains a convolutional neural network with the loss function and a plurality of images of a dataset to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales. The system can align an attribute of an image of the dataset by the trained neural network.
1. A computer vision system for performing noisy contour alignment comprising:
a memory; and
a processor in communication with the memory, the processor:
generating a loss function;
training a neural network using the loss function and a a dataset including plurality of images to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales; and
aligning an attribute of an image of the dataset using the trained neural network.
2. The system of claim 1 , wherein the processor determines an upper bound of the loss function.
3. The system of claim 1 , wherein the loss function is a local shape-dependent Chamfer upper bound loss function that measures proximity and local shape similarity.
4. The system of claim 1 , wherein the processor trains the neural network by:
extracting features of a source and target image pair of the dataset at different scales,
utilizing warp predictors to determine forward transforms to align source to target features at each scale, and
applying the loss function to determine backward transforms to align target to source features at each scale.
5. The system of claim 1 , wherein the neural network is a convolutional neural network.
6. The system of claim 1 , wherein the dataset is a Modified National Institute of Standards and Technology (MNIST) digit image dataset or a geo-parcel to aerial image alignment dataset.
7. The system of claim 1 , where the processor aligns a noisy digit contour present in the image or a parcel present in the image.
8. A method for performing noisy contour alignment by a computer vision system, comprising the steps of:
generating a loss function;
training a neural network using the loss function and a dataset including a plurality of images to learn to align noisy contours with progressively increasing complex forward and backward transforms over increasing scales; and
aligning an attribute of an image of the dataset using the trained neural network.
9. The method of claim 8 , further comprising the step of determining an upper bound of the loss function.
10. The method of claim 8 , wherein the loss function is a local shape-dependent Chamfer upper bound loss function that measures proximity and local shape similarity.
11. The method of claim 8 , further comprising the steps of training the neural network by
extracting features of a source and target image pair of the dataset at different scales,
utilizing warp predictors to determine forward transforms to align source to target features at each scale, and
applying the loss function to determine backward transforms to align target to source features at each scale.
12. The method of claim 8 , wherein the neural network is a convolutional neural network.
13. The method of claim 8 , wherein the dataset is a Modified National Institute of Standards and Technology (MNIST) digit image dataset or a geo-parcel to aerial image alignment dataset.
14. The method of claim 8 , further comprising the step of aligning the attribute of the image of the dataset by the trained neural network by aligning a noisy digit contour present in the image or a parcel present in the image.
15. A non-transitory computer readable medium having instructions stored thereon for performing noisy contour alignment by a computer vision system which, when executed by a processor, causes the processor to carry out the steps of:
generating a loss function;
training a neural network using the loss function and a a dataset including plurality of images to learn to align noisy contours with progressively increasing complex forward and backward transforms over increasing scales; and
aligning an attribute of an image of the dataset using the trained neural network.
16. The non-transitory computer readable medium of claim 15 , the processor further carrying out the step of determining an upper bound of the loss function.
17. The non-transitory computer readable medium of claim 15 , wherein the loss function is a local shape-dependent Chamfer upper bound loss function that measures proximity and local shape similarity.
18. The non-transitory computer readable medium of claim 15 , the processor further carrying out the step of training the neural network by:
extracting features of a source and target image pair of the dataset at different scales,
utilizing warp predictors to determine forward transforms to align source to target features at each scale, and
applying the loss function to determine backward transforms to align target to source features at each scale.
19. The non-transitory computer readable medium of claim 15 , wherein the neural network is a convolutional neural network.
20. The non-transitory computer readable medium of claim 15 , the processor further carrying out the step of aligning the attribute of the image of the dataset by the trained neural network by aligning a noisy digit contour present in the image or a parcel present in the image.