MahaBhulekh - Maharashtra 7/12 Satbara Land Record Extracts

MH Specific MH Subset Needed

Maharashtra's digitized land record system containing 2.11 crore (21.1 million) 7/12 satbara extracts across 358 talukas. Each extract follows a standardized Marathi template with structured fields for survey number, land area, landowner details, crop information, and encumbrances. The records are dynamically generated in Marathi and represent one of the largest standardized Marathi document sources available. Raw unannotated source requiring OCR ground-truth annotation, but the consistent template format makes automated annotation feasible. A community scraping tool exists for aggregation.

Build an annotation pipeline converting MahaBhulekh 7/12 extracts into field-level OCR training data with bounding boxes and transcriptions.

Maharashtra subset not yet extracted. This is a global dataset that contains data covering Maharashtra. A regional subset can be extracted by filtering on geographic coordinates or administrative boundaries.

Homepage GitHub Download

Quick Start

# MahaBhulekh - Maharashtra Land Records
# Browse: https://bhulekh.mahabhumi.gov.in/
# Digital Satbara: https://digitalsatbara.mahabhumi.gov.in/
# Aggregation tool: https://github.com/answerquest/mahabhulekh-7-12-aggregating

print("MahaBhulekh: 21.1M digitized 7/12 land records")
print("Standardized Marathi template - ideal for form OCR training")

Modality

Document images (standardized Marathi form template, unannotated)

Size

21.1 million digitized extracts; 358 talukas; all 36 districts

License

Gov Open

Format

HTML / PDF (dynamically generated)

Language

Update Frequency

continuous

Organization

Maharashtra Revenue Department, Government of Maharashtra

Schema

Field	Type	Description
survey_number	string	Land survey number
village	string	Village name in Marathi
taluka	string	Taluka name
district	string	District name
landowner_name	string	Landowner name in Marathi
land_area	float	Land area in hectares/ares
crop_type	string	Current crop or land use

Build With This

Create a FUNSD-style key-value extraction dataset for Marathi using 7/12 extract templates as the annotation base

Develop an automated land record search system that OCRs scanned satbara documents and makes them searchable

Build a land dispute analyzer extracting ownership history from sequences of 7/12 extracts for the same survey number

AI Use Cases

Marathi government form OCR training data sourceStructured document field extraction for DevanagariLand record digitization and searchabilityTemplate-based document understanding model training

Related Datasets

AIKOSH IIT Bombay Indic Datasets (IndiaAI)

multimodal

Bharat Scene Text Dataset (BSTD)

Image (scene text)

CHIPS - Corpus of Handwritten Indic Scripts (Page-Level OCR)

Image (full-page handwritten documents with detection + recognition annotations)

CMATERdb - Devanagari-Roman Mixed-Script Handwritten Documents

Image (handwritten mixed-script document pages with word-level annotations)

Last verified: 2026-03-12