{"id":"https://openalex.org/W4379653940","doi":"https://doi.org/10.1117/12.2680090","title":"Image calibration using ensemble of transformer and CNN-based frameworks","display_name":"Image calibration using ensemble of transformer and CNN-based frameworks","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379653940","doi":"https://doi.org/10.1117/12.2680090"},"language":"en","primary_location":{"id":"doi:10.1117/12.2680090","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2680090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth International Conference on Machine Vision (ICMV 2022)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070641408","display_name":"Anuj Kumar","orcid":"https://orcid.org/0000-0002-1785-370X"},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anuj Kumar","raw_affiliation_strings":["Indian Institute of Technology Jammu (India)"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu (India)","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081460480","display_name":"Sankar Behera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sankar Behera","raw_affiliation_strings":["Indian Institute of Technology Jammu (India)"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu (India)","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060469822","display_name":"Yamuna Prasad","orcid":"https://orcid.org/0000-0002-3709-7956"},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yamuna Prasad","raw_affiliation_strings":["Indian Institute of Technology Jammu (India)"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu (India)","institution_ids":["https://openalex.org/I4210127441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070641408"],"corresponding_institution_ids":["https://openalex.org/I4210127441"],"apc_list":null,"apc_paid":null,"fwci":0.1627,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47469947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7643861770629883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6904376149177551},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5982915759086609},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5115850567817688},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4690917730331421},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4567599892616272},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45589566230773926},{"id":"https://openalex.org/keywords/camera-resectioning","display_name":"Camera resectioning","score":0.41169142723083496}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7643861770629883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904376149177551},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5982915759086609},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5115850567817688},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4690917730331421},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4567599892616272},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45589566230773926},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.41169142723083496},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2680090","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2680090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth International Conference on Machine Vision (ICMV 2022)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4375867731","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W2379530911"],"abstract_inverted_index":{"Image":[0],"distortion":[1,45,120],"is":[2,13],"a":[3,14,103,109,146],"problem":[4],"due":[5],"to":[6,30,97,114,122,159],"wide":[7],"field-of-view":[8],"cameras,":[9],"and":[10,26,44,61,75,94,119,138],"camera":[11,27,38],"calibration":[12],"fundamental":[15],"step":[16],"in":[17,102,177],"various":[18,130,142],"applications":[19],"such":[20,40],"as":[21,41],"image":[22,35,53],"undistortion,":[23],"3D":[24],"reconstruction,":[25],"motion":[28],"estimation":[29],"overcome":[31,123],"this":[32,124],"problem.":[33,125],"In":[34],"calibration,":[36],"intrinsic":[37],"parameters":[39,121],"focal":[42,59,117],"length":[43,60,118],"are":[46,77,85],"estimated.":[47],"The":[48,126,150,164],"quality":[49],"of":[50,58,67,179],"the":[51,56,88,99,116,154,161,168,172],"undistorted/enhanced":[52],"depends":[54],"on":[55,87],"correctness":[57],"distortion.":[62],"However,":[63],"existing":[64],"methods":[65],"consist":[66],"two":[68],"approaches:":[69],"checkerboard,":[70],"which":[71],"requires":[72],"manual":[73],"interaction,":[74],"others":[76],"deep":[78,174],"learning":[79],"approaches.":[80],"Most":[81],"Deep":[82],"Learning":[83],"approaches":[84],"based":[86],"Convolution":[89],"Neural":[90],"Network":[91],"(CNN)":[92],"framework,":[93],"it":[95],"fails":[96],"capture":[98],"long-term":[100],"dependency":[101],"distorted":[104],"image.":[105,149],"This":[106],"paper":[107],"proposes":[108],"fully":[110],"automated":[111],"EnsembleNet":[112,170],"method":[113],"infer":[115],"proposed":[127,151,169],"model":[128,152],"extracts":[129],"contexts":[131],"(local":[132],"patches)":[133],"by":[134],"exploiting":[135],"ViT(Vision":[136],"Transformer)":[137],"spatial":[139],"features":[140],"from":[141],"CNN-based":[143],"models":[144,176],"using":[145],"single":[147],"input":[148],"uses":[153],"differential":[155],"evolution":[156],"(DE)":[157],"approach":[158],"learn":[160],"ensemble":[162],"weights.":[163],"experiments":[165],"show":[166],"that":[167],"outperforms":[171],"state-of-the-art":[173],"learning-based":[175],"terms":[178],"mean":[180],"squared":[181],"error.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}