| Description: |
Deprecated, please go to: https://doi.org/10.5281/zenodo.15110646 The automatic detection of tree-ring boundaries and other anatomical features using image analysis has progressed substantially over the past decade with advances in machine learning and imagery technology, as well as increasing demands from the dendrochronology community. This paper presents a publicly available database of 64 scanned images of transverse sections of commercially grown Pinus taeda trees from northern Uruguay, ranging from 17 to 24 years old. The collection contains several challenging features for automatic ring detection, including illumination and surface preparation variation, fungal infection (blue stains), knot formation, missing cortex or interruptions in outer rings, and radial cracking. This dataset can be used to develop and test automatic tree ring detection algorithms. The dataset was used to develop the Cross-Section Tree-Ring Detection (CS-TRD) method. ; The UruDendro data set is organized in several files, containing the images and the marks as described in below table. Name Size Format Example Explanation images.zip 396.2 MB png F02c.png Original Images images_no_background.zip 254.2 MB png F02c.png Disk masked image latewood_annotations.zip 11 MB json F02c.json Late wood annotations earlywood_annotations.zip json Early wood annotations reactionwood_annotations.zip json Reaction wood annotations pith_location.csv 916 bytes csv pith position In the images.zip file, there is an image per disk sample; in images_no_background.zip, there is an image per disk sample but without the disk background. In latewood_annotations.zip there are 5 differents annotations types. The file convention goes as follows: IMAGENAME-ANNOTATOR.json, IMAGENAME refers to the image sample identifier. ANNOTATOR is the expert who annotated the file: V, M, S and C. The file IMAGENAME.json is the ring average annotation between experts. In the earlywood_annotations.zip, there is an annotation file for each disk sample. IMAGENAME.json, IMAGENAME ... |