BeeBetビーベットとは？評判やボーナス、登録方法などを ...

etlcdb Skip to content Home About Download Contact Specification of ETL-9 ETL-9G Format Fixed-length records length without control sequence 8 bits per byte, 8199 bytes per record Big endian File formats and sample script Files One data set contains 3036 characters written by a writer, hence 12144 = 4 * 3036 20 sheets per writer: like 1-20: first writer, 21-40: second writer etc. filename # records # categories # data sets data set indices # sheets ETL9G_01 12144 3036 4 1-4 80 ETL9G_02 12144 3036 4 5-8 80 ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ETL9G_50 12144 3036 4 197-200 80 Samples filename record metadata and JIS code in hex image ETL9G_01 1 (1, 12321, &＃8216;A.TSUGU &＃8216;, 1, 0, 0, 0, 0, 0, 0, 8212, 8310, 0, 0) 0x3021 ETL9G_11 101 (1, 12580, &＃8216;IN.HIBI &＃8216;, 101, 0, 0, 0, 0, 0, 0, 8212, 8311, 4, 6) 0x3124 ETL9G_21 201 (2, 12839, &＃8216;OU.OKI &＃8216;, 49, 0, 0, 0, 0, 0, 0, 8212, 8406, 0, 3) 0x3227   ETL9G_31 301 (2, 13101, &＃8216;KAI.BAI &＃8216;, 301, 0, 0, 0, 0, 0, 0, 8212, 8405, 4, 9) 0x332d   ETL9G_41 401 (3, 13360, &＃8216;KAN.MA &＃8216;, 401, 0, 0, 0, 0, 0, 0, 8212, 8403, 0, 6) 0x3430 ETL-9B ETL-9B is generated from ETL-9G by binalization. The threshold is determined by T=λ∙h + (1-λ)∙μ, where h is Otsu&＃8217;s threshold [4] and μ is the average of all intensity levels in ETL-9G [5]. For ETL-9B, λ=0.4 [1][2]. Format File formats and sample script Files One data set contains 3036 characters written by a writer, hence 121440 = 40 * 3036 20 sheets per writer: 1-20: first writer, 21-40: second writer etc. The first record of each file is dummy filled by zeros The last data set of 3036 records of ETL9B_5 is the model presented to examinees filename # records # data sets data set index # sheets ETL9B_1 121440 40 1-40 800 ETL9B_2 121440 40 41-80 800 ETL9B_3 121440 40 81-120 800 ETL9B_4 121440 40 121-160 800 ETL9B_5 121440+3036 40+1 161-200 800+20 Samples filename record index (dummy record as 0) metadata and JIS code in hex image ETL9B_1 1 (1, 9250, &＃8216;A.HI&＃8217;) 0x2422 ETL9B_2 100 (801, 12349, &＃8216;AYA.&＃8217;) 0x303d ETL9B_3 200 (1601, 12611, &＃8216;EI.A&＃8217;) 0x3143 ETL9B_4 300 (2402, 12873, &＃8216;KA.Y&＃8217;) 0x3249 ETL9B_5 400 (3203, 13135, &＃8216;KAKU&＃8217;) 0x334f References 斉藤泰一、山田博三、山本和彦: &＃8220;JIS第1水準手書漢字データベースETL9とその解析&＃8221;, 「信学論(D) 画像処理特集号」, Vol.J68-D, No.4, pp.757&＃8211;764 (1985-04). 斉藤泰一、山田博三、山本和彦: &＃8220;手書文字データベースの解析(VIII) －方向パターン・マッチング法によるJIS第1水準手書漢字データベースETL9の評価－&＃8221;, 「電総研彙報」, Vol.49, No.7, pp.487&＃8211;525 (1985-07). 斉藤泰一、山本和彦、山田博三: &＃8220;手書文字データベースの解析(IX) －データベースETL9とその見本文字について－&＃8221;, 「電総研彙報」, Vol.50, No.4, pp.259&＃8211;263 (1986-04). 大津展之: &＃8220;判別および最小2乗規準に基づく自動しきい値選定法&＃8221;, 「信学論(D)」, Vol.63-D, No.4, pp.349&＃8211;356 (1980-04). 斉藤泰一、山田博三: &＃8220;判別しきい値選定法の一改良&＃8221;, 「情報処理学会論文誌(情処学論)」, Vol.22, No.6, pp.596&＃8211;599 (1981-11). Language: English 日本語 Iconic One Theme | Powered by Wordpress