Evaluation and comparison of open source program solutions for automatic seed counting on digital images

ImageJ, CellProfiler, P-TRAP and SmartGrain evaluated for seed counting from digital images.ImageJ seed counting macro evaluated with RenyiEntropy threshold.Results differ, firstly by image-analysis program and secondly by crop species.CellProfiler and P-TRAP showed suitable performance for seed counting.Benchmark showed lowest time required by SmartGrain and longest by P-TRAP. Seed number quantification is an essential agronomic parameter conducted mostly manually or by mechanical counters, both with obvious limitations. Digital image analysis provides a reliable and robust alternative to accurately calculate many biological features. This study presents and evaluates the performance of four open-source image-analysis programs i.e. ImageJ, CellProfiler, P-TRAP and SmartGrain to count crop seeds from digital images captured by camera and scanner. It also evaluates ImageJ program for automated seed counting using macro containing RenyiEntropy threshold algorithm. Digital images of cereal crop seeds were acquired i.e. wheat, barley, maize, rye, oat, sorghum, triticale and rice. All images contained 200 seeds per image present in an area of approx. 1400cm2. RenyiEntropy threshold increased the seed count accuracy of ImageJ from digital camera images. Generally, seed counts from digital camera images of all crops were accurate, but software-crop combination had significant (p<0.05) difference from reference value. Among image analysis programs, ImageJ produced mostly higher seed count across all observed crops than other programs. Mean seed counts from scanned images of maize were observed only by CellProfiler and P-TRAP, with other programs inappropriate due to high inaccuracy. These results suggest CellProfiler as a reliable image analysis program for seed counting from digital images. Benchmark test was also performed to compare speed of analysis. The automated seed count produced by image analysis programs described here allows faster, reliable and reproducible analysis, compared to standard manual method. To our knowledge this is the first study on using CellProfiler program for crop seed counting from digital images.

[1]  S. Takumi,et al.  Identification of quantitative trait loci controlling grain size and shape in the D genome of synthetic hexaploid wheat lines , 2013, Breeding science.

[2]  A. Greenberg,et al.  High-Resolution Inflorescence Phenotyping Using a Novel Image-Analysis Pipeline, PANorama1[W][OPEN] , 2014, Plant Physiology.

[3]  Geoffrey J. Hay,et al.  Object-based Image Analysis : Strengths , Weaknesses , Opportunities and Threats ( Swot ) , 2006 .

[4]  Dennis Jarvis,et al.  Estimating mango crop yield using image analysis using fruit at 'stone hardening' stage and night time imaging , 2014 .

[5]  Gurdial Arora,et al.  A thresholding method based on two-dimensional Renyi's entropy , 2004, Pattern Recognit..

[6]  Y. Suputtamongkol,et al.  Application of ImageJ program to the enumeration of Orientia tsutsugamushi organisms cultured in vitro , 2012, Transactions of the Royal Society of Tropical Medicine and Hygiene.

[7]  Suann Yang,et al.  Counting pollen grains using readily available, free image processing and analysis software. , 2009, Annals of botany.

[8]  Riichi Kajiwara,et al.  Counting contacts between neurons in 3D in confocal laser scanning images , 2008, Journal of Neuroscience Methods.

[9]  L. Borrás,et al.  Counting Maize Kernels through Digital Image Analysis , 2011 .

[10]  W. Batchelor,et al.  Shape identification and particles size distribution from basic shape parameters using ImageJ , 2008 .

[11]  Kevin W Eliceiri,et al.  NIH Image to ImageJ: 25 years of image analysis , 2012, Nature Methods.

[12]  Christophe Jourdan,et al.  IJ_Rhizo: an open-source software to measure scanned images of root samples , 2013, Plant and Soil.

[13]  A. Mittag,et al.  Morphometry to identify subtypes of leukocytes. , 2014, Hematology/oncology and stem cell therapy.

[14]  A. Anjos,et al.  P-TRAP: a Panicle Trait Phenotyping tool , 2013, BMC Plant Biology.

[15]  Sandra J Shefelbine,et al.  BoneJ: Free and extensible bone image analysis in ImageJ. , 2010, Bone.

[16]  J E González,et al.  Automatic analysis of silver-stained comets by CellProfiler software. , 2012, Mutation research.

[17]  E. Uberbacher,et al.  A segmentation algorithm for noisy images , 1996, Proceedings IEEE International Joint Symposia on Intelligence and Systems.

[18]  M. Yano,et al.  SmartGrain: High-Throughput Phenotyping Software for Measuring Seed Shape through Image Analysis1[C][W][OA] , 2012, Plant Physiology.

[19]  Douglas E. Karcher,et al.  The Assessment of Leaf Nitrogen in Corn from Digital Images , 2011 .

[20]  C. Tétard-Jones,et al.  The effect of organic and conventional management on the yield and quality of wheat grown in a long-term field trial , 2013 .

[21]  B. Sakmann,et al.  Journal of Neuroscience Methods Automated Three-dimensional Detection and Counting of Neuron Somata , 2022 .

[22]  Anne E Carpenter,et al.  CellProfiler: image analysis software for identifying and quantifying cell phenotypes , 2006, Genome Biology.

[23]  Yoichiro Kato,et al.  Comparison of threshold algorithms for automatic image processing of rice roots using freeware ImageJ , 2011 .

[24]  D. J. Buckley,et al.  A photoelectric seed counting detector , 1976 .

[25]  Ying Xu,et al.  A segmentation algorithm for noisy images: Design and evaluation , 1998, Pattern Recognit. Lett..

[26]  Wei Wang,et al.  Extended-Maxima Transform Watershed Segmentation Algorithm for Touching Corn Kernels , 2013 .