Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2103.07676

uTHCD: A New Benchmarking for Tamil Handwritten OCR

Noushath Shaffi·Faizal Hajamohideen
View original source ↗Read source document ↗Export metadata ↓

Abstract

Handwritten character recognition is a challenging research in the field of document image analysis over many decades due to numerous reasons such as large writing styles variation, inherent noise in data, expansive applications it offers, non-availability of benchmark databases etc. There has been considerable work reported in literature about creation of the database for several Indic scripts but the Tamil script is still in its infancy as it has been reported only in one database [5]. In this paper, we present the work done in the creation of an exhaustive and large unconstrained Tamil Handwritten Character Database (uTHCD). Database consists of around 91000 samples with nearly 600 samples in each of 156 classes. The database is a unified collection of both online and offline samples. Offline samples were collected by asking volunteers to write samples on a form inside a specified grid. For online samples, we made the volunteers write in a similar grid using a digital writing pad. The samples collected encompass a vast variety of writing styles, inherent distortions arising from offline scanning process viz stroke discontinuity, variable thickness of stroke, distortion etc. Algorithms which are resilient to such data can be practically deployed for real time applications. The samples were generated from around 650 native Tamil volunteers including school going kids, homemakers, university students and faculty. The isolated character database will be made publicly available as raw images and Hierarchical Data File (HDF) compressed file. With this database, we expect to set a new benchmark in Tamil handwritten character recognition and serve as a launchpad for many avenues in document image analysis domain. Paper also presents an ideal experimental set-up using the database on convolutional neural networks (CNN) with a baseline accuracy of 88% on test data.

Explore related subjects

cs.CVcs.LG

Keep this discovery

BibTeXRIS

Noushath Shaffi, Faizal Hajamohideen. 2021-03-13. uTHCD: A New Benchmarking for Tamil Handwritten OCR. https://doi.org/10.1109/access.2021.3096823

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

HiPerViT: A Hierarchical Perceiver-Vision Transformer Architecture for Multi-Scale Texture Recognition

Texture recognition remains challenging for modern vision models because discriminative evidence is often carried by higher-order spatial statistics rather than by object shape alone. While Vision Transformers provide strong long-range modeling capacity, their standard object-centric representations do not explicitly expose such statistical structure, which limits texture sensitivity in fine-grained recognition settings. We present HiPerViT, a compact vision-only architecture that injects an explicit second-order statistical prior into a transformer-based recognition pipeline. The method combines global and local image views with a compact bilinear descriptor encoded as a statistical token, and integrates this token with first-order spatial representations through Perceiver-style latent distillation. This design enables direct interaction between spatial tokens and second-order feature co-occurrence statistics, providing the model with explicit access to texture-relevant information without requiring multimodal pretraining or ensemble construction. Across six texture recognition benchmarks, HiPerViT achieves consistent improvements over strong vision-only baselines under the reported evaluation protocols, including gains of +3.05 percentage points on DTD, +10.48 on GTOS-Mobile, and +10.10 on 1200Tex. Beyond benchmark performance, our analyses show that these gains are largely invariant to the backbone depth used to extract second-order statistics and to the ordering of interaction and distillation stages. This pattern suggests that the primary source of improvement is not a specific fusion topology, but the explicit availability of second-order statistical information as a first-class representational signal. These results support explicit statistical tokenization as an effective and robust design principle for texture-centric visual recognition.

cs.CV↗
arXiv2026

CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation

The integration of large language models (LLMs) into video generation has enabled rapid text-to-video creation and improved visual quality. However, it still falls short of professional filmmaking, where cinematographic language is less refined than human-crafted camera work and multi-shot continuity remains challenging. To address these limitations, we introduce CamPilot, a multi-agent framework that integrates cinematographic planning and camera-work control to produce more coherent, logically structured, and human-aesthetic movies. CamPilot adopts a GRPO-based learning paradigm to learn camera work planning from 14K real-world professional movies, internalizing motion patterns and composition principles that support reasoning over shooting techniques (e.g., camera angle, motion, and focal behavior) and cross-shot relationships for controllable camera-viewpoint generation. Multiple agents further collaborate and evolve to improve overall output quality. To support this work and further studies in this domain, we establish CamEval, a benchmark for evaluating camera work quality and cinematic engagement. Empirical results show that CamPilot outperforms state-of-the-art text-to-movie generation methods on cinematographic control and quality, highlighting the impact of professional camera design on movie generation.

cs.CV↗
arXiv2026

New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models

A model first sees an image from one physical measurement experiment, such as how far a block coasted, and must answer a question about a new trial, such as whether the block will pass a target after a fixed push. The initial experiment may provide enough information to answer, or the model may need another measurement, such as the object's mass, friction, restitution, or spring stiffness. We study whether vision language models can decide when to answer immediately and, when more evidence is needed, which experiment to perform. Current physical reasoning benchmarks usually evaluate only the final answer, so they do not directly measure this decision-making ability. We introduce a controlled evaluation where each problem provides one measurement image and four possible physical worlds created by combining two possible masses and two possible values of another relevant property. The model must either stop and answer or select the cheapest additional experiment that can resolve the question. We construct matched problem pairs where changing either the observed measurement or the question changes the optimal action. Since all possible worlds and experiment costs are known, we can explicitly determine the optimal choice. Across six open models and 144 physical parameter sets, direct responses repeat the same action for 95.1% to 100% of image pairs even when the correct action changes. Brief reasoning improves action switching, but the best model makes both decisions correctly for only 5.9% of image pairs. Additional analysis reveals failures in measurement interpretation, physical reasoning, and response formatting. By evaluating evidence selection separately from final answers, our benchmark reveals limitations in physical reasoning that conventional answer accuracy can overlook.

cs.CV↗