Image scene recognition
Systems, methods, and computer program products may be directed to creating an image hash. Key points can be identified at different locations within a sample image. Descriptor vectors for the key points can be identified, the descriptor vectors describing local image information around the key points, where each descriptor vector is an n-dimensional array. Key points can be generated based on hashes of data vectors that include at least one of the descriptors, where each feature is a 36×20 hash value.
1. A method of creating an image hash, comprising:
identifying features at different locations within a sample image;
identifying descriptor vectors for at least a subset of the features, the subset defining key points of the image, the descriptor vectors describing local image information around the key points, where each descriptor vector is an n-dimensional array and is represented as a unary feature of dimension 128×128; and
generating key points based on hashes of data vectors that include at least one of the descriptors, where each feature is a 36×20 hash value.
2. The method of claim 1 , wherein the hashes are performed using a hash function for which a probability that the hash of an arbitrary first vector corresponds to the hash of an arbitrary second vector is a function of a range between the first vector and the second vector.
3. The method of claim 2 , wherein the hash function generates a characteristic data string from a data vector larger than the characteristic data string, wherein the arbitrary first vector is a first descriptor vector, and the arbitrary second vector is a second descriptor vector.
4. The method of claim 2 , wherein each feature corresponds to multiple keypoints, and each feature is a 36×20 has value.
5. The method of claim 1 , wherein each feature comprises:
a hash value of a first descriptor vector for a first keypoint,
a hash value of a second descriptor vector for a second key point,
a first quantization function mapping an orientation of the first key point in relation to the second key point to a range of integers, and
a second quantization function mapping an orientation of the second key point in relation to the first key point to the range of integers.
6. The method of claim 1 , further comprising executing a quantization function mapping an orientation of each key point to a range of integers.
7. The method of claim 1 , wherein each hash value is calculated by using a fast algorithm in combination with a sift algorithm.
8. The method of claim 1 , wherein each key point is obtained using a fast algorithm.
9. The method of claim 1 , wherein each descriptor vector is obtained using a sift algorithm.