Paul W. Palumbo

Document Image Binarization: Evaluation Of Algorithms

The extraction of a binary image from a gray level image is a common image processing operation particularly for document image analysis and optical character recognition. Various methods for this task are described in the literature including global and adaptive binarization. This paper evaluates three adaptive binarization techniques viz., a contrast measure approach, a weighted running average approach and a second derivative approach, and compares them to global binarization methods. Experiments with noisy document (postal letter mail) images lead to the following conclusions. Image contrast binarization often yields nearly the same results as the edge operator, with considerably less computation and is less sensitive to parameter settings. In addition, the edge operator is more sensitive to image resolution than the contrast operator. The weighted running-average approach is highly sensitive to the parameters involved in the calculation of the average but produces a quick binarization.

Postal address block location in real time

The CEDAR real-time address block location system, which determines candidates for the location of the destination address from a scanned mail piece image, is described. For each candidate destination address block (DAB), the address block location (ABL) system determines the line segmentation, global orientation, block skew, an indication of whether the address appears to be handwritten or machine printed, and a value indicating the degree of confidence that the block actually contains the destination address. With 20-MHz Sparc processors, the average time per mail piece for the combined hardware and software system components is 0.210 seconds. The system located 89.0% of the addresses as the top choice. Recent developments in the system include the use of a top-down segmentation tool, address syntax analysis using only connected component data, and improvements to the segmentation refinement routines. This has increased top choice performance to 91.4%.<<ETX>>

A special-purpose content addressable memory chip for real-time image processing

An application specific integrated circuit (ASIC) using a special-purpose content addressable memory that performs parallel search and multiple update (PSMU) operation is presented. This chip, referred to as multiple update content addressable memory (MUCAM), can search 256, 8-b-wide locations in parallel for target data and update all such locations with new data within 50 ns. MUCAM has been developed for image component labeling and merging operation in a connected component analyzer. It was fabricated using 0.9- mu m CMOS technology. >

A blackboard-based approach to handwritten ZIP code recognition

A methodology for recognizing ZIP codes (US postal codes) in handwritten addresses is presented that uses many diverse pattern recognition and image processing algorithms. Given a high-resolution image of a handwritten address block, the solution invokes routines capable of hypothesizing the location of the ZIP code, segmenting and recognizing ZIP code digits, locating and recognizing city and state names, and looking up the results in a dictionary. The control structure is not strictly sequential, but rather in the form of a blackboard architecture that opportunistically invokes routines as needed. An implementation of the methodology is described as well as results with a database of grey-level images of handwritten addresses (taken from live mail in a US Postal Service mail processing facility). Future extensions of the approach are discussed.<<ETX>>

Object recognition in visually complex environments: an architecture for locating address blocks on mail pieces

A method of recognizing an object of interest in a complex visual environment is described. Motivated by the problem of finding the destination address block on a piece of mail, a general framework for coordinating a collection of specialized image analysis tools is described. The resulting system can deal with a wide range of environments: from those having a high degree of global spatial structure (e.g. mail envelopes which conform to specifications) to those with no structure (e.g. magazines with randomly pasted address labels). The problem-solving architecture accounts for uncertainty in the imaging environment by using the blackboard model. The system consists of several specialized tools and a control structure so that the tools are opportunistically invoked and coordinated. Its performance on an image database of difficult cases is described.<<ETX>>

Contrast Enhancement of Mail Piece Images

A New approach to contrast enhancement of mail piece images is presented. The contrast enhancement is used as a preprocessing step in the real-time address block location (RT-ABL) system. The RT-ABL system processes a stream of mail piece images and locates destination address blocks. Most of the mail pieces (classified into letters) show high contrast between background and foreground. As an extreme case, however, the seasonal greeting cards usually use colored envelopes which results in reduced contrast osured by an error rate by using a linear distributed associative memory (DAM). The DAM is trained to recognize the spectra of three classes of images: with high, medium, and low OCR error rates. The DAM is not forced to make a classification every time. It is allowed to reject as unknown a spectrum presented that does not closely resemble any that has been stored in the DAM. The DAM was fairly accurate with noisy images but conservative (i.e., rejected several text images as unknowns) when there was little ground and foreground degradations without affecting the nondegraded images. This approach provides local enhancement which adapts to local features. In order to simplify the computation of A and (sigma) , dynamic programming technique is used. Implementation details, performance, and the results on test images are presented in this paper.

Address block location using character recognition and address syntax

The authors shown many advantages of using postal syntactic features in address block location. Performing character recognition at low resolution (100 PPI) is desirable for a real-time system. An efficient word matching algorithm is designed to match words against a dictionary of about 500 keywords and assign a syntactic tag to each word in a text block. The critical information and the street syntax are extracted by parsing the syntactic tags. The usage of the postal syntactic features has been introduced in many aspects such as recovering lost information, selecting a more likely destination address block, and improving destination address block segmentation. With character recognition available in the system, the utilization of other syntax and context information on the mail pieces becomes feasible. The initial testing results of the incorporation of the syntactic processing in address block location were positive and encouraging.<<ETX>>

Special purpose register array for real-time image processing

An ASIC which implements a special purpose register array for real-time application has been presented. This chip, referred to as MUCAM, performs parallel searches and multiple updates of up to 256 8-bit data within 52 ns. MUCAM has been developed for image component labeling, and merge operation in a connected component analyzer. It has been fabricated using 0.9 mu m CMOS technology.<<ETX>>

Image processing ASIC for real-time contrast enhancement

An ASIC chip set that implements adaptive local contrast enhancement for real-time image processing is presented. The contrast enhancement is based on a nonlinear mapping M(A, sigma ,P), where A is an average, sigma is a standard deviation, and P is a center pixel over a 9*9 window. The throughput rate is 100 ns per pixel. A dynamic programming technique and pipelining are used to minimize the space-time constraint in the implementation.<<ETX>>

Multi-attribute lexicon generation by hyperlinked embedded access structure

Providing a lexicon for all possible postal addresses can support decision making for handwritten address interpretation. The possibility of uncertainty can be reduced by choosing the highest confident record in the provided lexicon as the target postal address. For a large database with multi-attribute records, traditional access methods are not efficient enough to generate the lexicon. This paper proposes a hyperlinked embedded access structure (HEAS) which combines the features of inverted file structure and doubly-chained tree structure with unique data compression schemes. The raw United State Postal Service (USPS) database is organized according to the proposed access structure, and the organized database serves as a knowledge base for interpreting handwritten addresses. The organization cost, storage requirement, and query cost are analyzed and compared to conventional inverted file and doubly-chained tree structures.