DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis

نویسندگان

چکیده

Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents novel approach, called DocSynth, to automatically synthesize based given layout. In this work, spatial layout (bounding boxes with categories) as reference by the user, our proposed DocSynth model learns generate set realistic consistent defined Also, framework has been adapted work superior baseline for creating synthetic datasets augmenting real data during training analysis tasks. Different sets learning objectives have also used improve performance. Quantitatively, we compare generated results using standard evaluation metrics. The highlight that can successfully diverse objects. We present comprehensive qualitative summary different scopes Lastly, knowledge first its kind.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Geometric Layout Analysis Techniques for Document Image Understanding: a Review

Document Image Understanding (DIU) is an interesting research area with a large variety of challenging applications. Researchers have worked from decades on this topic, as witnessed by the scientific literature. The main purpose of the present report is to describe the current status of DIU with particular attention to two subprocesses: document skew angle estimation and page decomposition. Sev...

متن کامل

A Layout - Analysis Based System for Document Image Retrieval ! ! !

Document Image Retrieval! !! G. Pirlo , M. Chimienti, M. Dassisti, D. Impedovo, A. Galiano !!!!!!! Abstract. This paper presents new system for document image retrieval, based on layout-analysis. The system, that is well suited for commercial form retrieval, uses Radon Transform for layout description and Dynamic Time Warping for document image matching. The experimental results, that were cond...

متن کامل

Document image understanding: geometric and logical layout

Document Image Understanding encompasses the technology required to make paper documents equivalent to other computer exchange media like oppies, tapes, and cdroms. The physical reader of the paper document is the scanner just like the physical reader of the oppy is the oppy drive and the physical reader of the tape cartridge is the tape cartridge drive, and the physical reader of the cdrom is ...

متن کامل

Document Image Layout Comparison and Classification

This paper describes features and methods for document image comparison and classification at the spatial layout level. The methods are useful for visual similarity based document retrieval as well as fast algorithms for initial document type classification without OCR. A novel feature set called interval encoding is introduced to capture elements of spatial layout. This feature set encodes reg...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Lecture Notes in Computer Science

سال: 2021

ISSN: ['1611-3349', '0302-9743']

DOI: https://doi.org/10.1007/978-3-030-86334-0_36