A Method of Text Extremum Region Extraction Based on Joint-Channels

Natural scene recognition has important significance and value in the fields of image retrieval,autonomous navigation,human-computer interaction and industrial automation.Firstly,the natural scene image non-text content takes up relatively high proportion;secondly,the natural scene images have a cluttered background and complex lighting conditions,angle,font and color.Therefore,how to extract text extreme regions efficiently from complex and varied natural scene images plays an important role in natural scene image text recognition.In this paper,a Text extremum region Extraction algorithm based on Joint-Channels(TEJC)is proposed.On the one hand,it can solve the problem that the maximum stable extremum region(MSER)algorithm is only suitable for gray images and difficult to process color images.On the other hand,it solves the problem that the MSER algorithm has high complexity and low accuracy when extracting the most stable extreme region.In this paper,the proposed algorithm is tested and evaluated on the ICDAR data set.The experimental results show that the method has superiority.

Comparative Analyses and Phylogenetic Relationships between Cryptomeria fortunei and Related Species Based on Complete Chloroplast Genomes

Cryptomeria fortunei(Chinese cedar)is a highly adaptable woody species and one of the main forest plantation trees in subtropical high-altitude areas in China.However,there are few studies on its chloroplast(cp)genome.In this study,the complete cp genome of C.fortunei was sequenced and evaluated via comparative analyses with those of related species(formerly the Taxodiaceae)in Cupressaceae.The C.fortunei cp genome was 131,580 bp in length,and the GC content of the whole genome was 35.38%.It lost one relevant large inverted repeat and contained 114 unique genes,including 82 protein-coding genes,28 tRNAs and 4 rRNAs.The relative synonymous codon usage(RSCU)of codons ending with A/U was more than twice that of codons ending with G/C.Thirty long repeat structures(LRSs)and 213 simple sequence repeat(SSR)loci were detected in the C.fortunei cp genome.Comparative analyses of 10 cp genomes revealed that substantial rearrangements occurred in the gene organization.Additionally,6 cp hotspot regions(trnS-GGA,ycf1,trnP-GGG,trnC-GCA,psbZ and accD)were identified,and 4 genes(petL,psbM,rpl22 and psaM)had likely underwent positive selection.Phylogenetic analysis showed that Cupressaceae,Taxaceae and Cephalotaxaceae clustered to form a clade and that C.fortunei was most closely related to C.japonica(Japanese cedar),C.japonica cv.Wogon Hort and Taxodium distichum(baldcypress).These results provide references for future studies of population genetics,phylogenetic status and molecular markers among Cupressaceae species and for the cultivation of improved varieties.

The nodule-specific transcriptional repressor Top Hub 4 regulates nodule structure and nitrogen fixation capacity in soybean

Most leguminous plants establish symbiotic relationships with rhizobia to form root organs called nodules(Ferguson et al.,2010).Nodules are specialized organs containing bacterial symbionts,which can provide enormous amounts of fixed nitrogen to their plant hosts(Peoples et al.,2009).Soybean(Glycine max),an economically important grain and oil crop,forms symbiotic nitrogen-fixing nodules,which reduces the demand for chemical nitrogen fertilizers and promotes yield(Saito et al.,2014).Nodule development is spatiotemporally regulated by the action of a number of transcription factors(TFs).

In silico prediction methods of self-interacting proteins:an empirical and academic survey

In silico prediction of self-interacting proteins(SIPs)has become an important part of proteomics.There is an urgent need to develop effective and reliable prediction methods to overcome the disadvantage of high cost and labor intensive in traditional biological wet-lab experiments.The goal of our survey is to sum up a comprehensive overview of the recent literature with the computational SIPs prediction,to provide important references for actual work in the future.In this review,we first describe the data required for the task of DTIs prediction.Then,some interesting feature extraction methods and computational models are presented on this topic in a timely manner.Afterwards,an empirical comparison is performed to demonstrate the prediction performance of some classifiers under different feature extraction and encoding schemes.Overall,we conclude and highlight potential methods for further enhancement of SIPs prediction performance as well as related research directions.