A Generic Method for Stamp Segmentation Using Part-Based Features

Abstract

Traditionally, stamps are considered as a seal of authenticity for documents. For automatic processing and verification, segmentation of stamps from documents is pivotal. Existing methods for stamp extraction mostly employ color and/or shape based techniques, thereby limiting their applicability to only colored and specific shape stamps. In this paper, a novel, generic method based on part-based features is presented for segmentation of stamps from document images. The proposed method can segment black, colored, unseen, arbitrary shaped, textual, as well as graphical stamps. The proposed method is evaluated on a publicly available dataset for stamp detection and verification and achieved recall and precision of 73% and 83% respectively, for black stamps which were not addressed in the past.

A spectral filtering based deep learning for detection of logo and stamp

“…The performance is also compared with techniques reported in [1] and [2] to detect stamps in a document. Average recall and average precision of [1] and [2] techniques, and the proposed SFDL algorithm are shown in Table 2.…”

“…The performance is also compared with techniques reported in [1] and [2] to detect stamps in a document. Average recall and average precision of [1] and [2] techniques, and the proposed SFDL algorithm are shown in Table 2. The stamp detection performance of the SFDL algorithm is better than the techniques reported in [1] and [2].…”

“…Average recall and average precision of [1] and [2] techniques, and the proposed SFDL algorithm are shown in Table 2. The stamp detection performance of the SFDL algorithm is better than the techniques reported in [1] and [2]. It may be noted that these techniques were meant for detecting stamps only.…”

“…The method is limited to non-black colored stamps of any shapes and forms. Ahmed et al [2] proposed a technique for stamp detection based on geometric features and key point descriptors that needs training to detect stamps both in black and white, and colored forms. However, it reported low precision and recall, as it was not able to handle severely overlapped stamps.…”

Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks

“…These digitized documents can be processed in an automated fashion given that the information contained in those documents can be extracted reliably. Reliable extraction of information from documents has been a major focus of the document analysis community for decades [1][2][3][4].…”