Systems and methods for stamp detection and classification
In some aspects, the disclosure is directed to methods and systems for detection and classification of stamps in documents. The system can receive image data and textual data of a document. The system can pre-process and filter that data, and covert the textual data to a term frequency inverse document frequency (TF-IDF) vector. The system can detect the presence of a stamp on the document. The system can extract a subset of the image data including the stamp. The system can extract text from the subset of the image data. The system can classify the stamp using the extracted text, the image data, and the TF-IDF vector. The system can store the classification in a database.
1. A method for stamp detection and classification, comprising:
receiving, by a computing device, textual data of a document and image data comprising a capture of the document;
identifying, by the computing device, a presence of a stamp on the document based on a plurality of intermediate detections of the stamp from the textual data and image data by a corresponding plurality of machine learning models;
responsive to identifying the presence of the stamp, extracting, by the computing device, a subset of the image data comprising the stamp;
extracting, by the computing device via optical character recognition, text from the subset of the image data; and
storing, by the computing device in a database, the subset of the image data comprising the stamp, the extracted text from the subset of the image data, and an identification of a classification of the stamp.
2. The method of claim 1 , further comprising converting, by the computing device, the image data to grayscale.
3. The method of claim 1 , further comprising downscaling, by the computing device, the grayscale image data to a predetermined size.
4. The method of claim 1 , further comprising:
filtering, by the computing device, the textual data to remove predetermined characters; and
converting, by the computing device, the textual data to a term frequency-inverse document frequency (TF-IDF) vector.
5. The method of claim 4 , wherein filtering the textual data further comprises applying a regular expression filter to the textual data.
6. The method of claim 4 , wherein filtering the textual data further comprises standardizing, by the computing device, at least one word of the textual data according to a predefined dictionary.
7. The method of claim 4 , wherein the TF-IDF vector is used as an input to the trained neural network.
8. The method of claim 1 , wherein the plurality of intermediate detections of the stamp from the textual data and image data are weighted and aggregated in a weighted ensemble model.
9. The method of claim 1 , further comprising classifying the stamp according to a ridge regression model.
10. The method of claim 1 , further comprising classifying the stamp as corresponding to one of a predetermined plurality of classifications.
11. A system configured for stamp detection and classification, the system comprising:
a computing device comprising one or more processors and a memory, configured to:
receive textual data of a document and image data comprising a capture of the document,
identify a presence of a stamp on the document responsive to a plurality of intermediate detections of the stamp from the textual data and image data by a corresponding plurality of machine learning models,
responsive to identifying the presence of the stamp, extract a subset of the image data comprising the stamp,
extract, via optical character recognition, text from the subset of the image data, and
storing, in a database, the subset of the image data comprising the stamp, the extracted text from the subset of the image data, and an identification of a classification of the stamp.
12. The system of claim 11 , wherein the computing device is further configured to convert the image data to grayscale.
13. The system of claim 11 , wherein the computing device is further configured to downscale the grayscale image data to a predetermined size.
14. The system of claim 11 , wherein the computing device is further configured to:
filtering the textual data to remove predetermined characters; and
convert the textual data to a term frequency-inverse document frequency (TF-IDF) vector.
15. The system of claim 14 , wherein the computing device is further configured to apply a regular expression filter to the textual data.
16. The system of claim 14 , wherein the computing device is further configured to standardize at least one word of the textual data according to a predefined dictionary.
17. The system of claim 14 , wherein the TF-IDF vector is used as an input to the trained neural network.
18. The system of claim 11 , wherein the plurality of intermediate detections of the stamp from the textual data and image data are weighted and aggregated in a weighted ensemble model.
19. The system of claim 11 , wherein the computing device is further configured to classify the stamp according to a ridge regression model.
20. The system of claim 11 , wherein the computing device is further configured to classify the stamp as corresponding to one of a predetermined plurality of classifications.