I'm currently looking for a good monospaced font and decided to use Tesseract's box.train as one referee.
So what I did was: 1) find some monospaced fonts 2) render 26 lines (each line containing all printable, non-whitespace ASCI characters) for font sizes 8px-26px 3) execute: tesseract xx.fontname.fonstize.tif xx.fontname.fonstize box.train.stderr 4) extract "good blobs" value 5) make a table ;) Intuitively I'd expect more good blobs at higher font sizes but ... Let's take Kochi Mincho as a sample: 8px 9px 10px 11px 12px 13px 14px 15px 16px 0 119 1232 1513 1732 1853 0 1461 1271 8px, 9px: no/few blobs - expected 10px-13px: increasingly more blobs - expected 14px: no blobs at all - quite unexpected I deliberately didn't check actual recognition rates and used no pre-processing. The attached console_shootout.txt contains the test results for 78 fonts. Thomas -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to tesseract-ocr@googlegroups.com To unsubscribe from this group, send email to tesseract-ocr+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to tesseract-ocr+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/groups/opt_out.
fontname 8px 9px 10px 11px 12px 13px 14px 15px 16px 17px 18px 19px 20px 21px 22px 23px 24px 25px 26px max(loss) min(stability) AR PL KaitiM Big5 0 1228 1624 1932 1983 2076 2137 2041 2179 2166 1975 2249 2230 2235 2258 2279 2176 2267 2277 -204 0.906 AR PL KaitiM GB 0 0 1772 1575 1651 1858 2096 2058 2168 2066 1939 2238 2206 2277 2206 2281 2281 2283 2265 -229 0.889 AR PL Mingti2L Big5 0 1277 1699 1399 1879 2005 2039 2116 2222 2234 2141 2260 2217 2238 2217 2276 2011 2262 2266 -300 0.823 AR PL New Kai 239 1359 1824 2087 1921 2126 2167 2072 1872 2204 2142 2256 2259 2261 2277 2266 2213 2277 2286 -295 0.864 AR PL New Kai ExtB 19 1228 1624 1932 1782 2029 2131 1929 2132 2166 1354 2208 2214 2224 2264 2252 2115 2262 2277 -812 0.625 AR PL New Sung Mono 438 875 630 2127 1776 2179 1591 2112 2238 2191 2234 2257 2272 2175 2278 2261 2237 2211 2171 -588 0.720 AR PL SungtiL GB 0 261 888 911 0 655 1669 1172 1353 0 0 2008 2157 2129 2103 2250 2239 2249 2216 -1669 0.000 AR PL UKai CN 303 749 1669 1969 1970 2093 2217 1992 2185 2197 2130 2245 2256 2192 2284 2273 1942 2282 2284 -342 0.850 AR PL UMing CN 287 1964 1870 0 1658 2027 2121 2132 2188 2175 2068 2270 2242 2262 2241 2276 2161 2257 2279 -1964 0.000 Aerial Mono 2019 2058 2165 2189 2190 2252 2252 2263 2285 2282 2280 2285 2287 2288 2281 2288 2285 2285 2288 -7 0.997 Andale Mono 1454 1968 2155 2168 2178 2152 2203 2221 2230 2210 2233 2194 2281 2288 2285 2287 2285 2286 2288 -39 0.983 Anonymous Pro 613 720 1541 2112 2130 2083 2177 2187 2201 2249 2254 2254 2213 2262 2236 2203 2284 2280 2282 -59 0.974 Bitstream Vera Sans Mono 1749 2038 2159 2179 2157 2258 2250 2259 2278 2270 2274 2274 2285 2283 2281 2288 2281 2285 2287 -22 0.990 CMU Typewriter Text Light 1573 1976 2009 2081 2134 2158 2126 2158 2199 2226 2216 2282 2268 2282 2287 2287 2288 2287 2288 -32 0.985 Courier 180 1611 1142 1943 2147 2142 2249 2199 2248 2257 2262 2283 2262 2281 2285 2284 2288 2286 2283 -469 0.709 Courier 10 Pitch 390 1624 2018 2142 2138 1972 2192 2167 2160 2214 2214 2245 2245 2259 2261 2266 2267 2285 2271 -170 0.921 Courier New 2047 2074 2121 2137 2186 2184 2198 2237 2240 2233 2262 2273 2269 2264 2276 2286 2287 2286 2287 -9 0.996 Cousine 233 1554 2185 2156 2205 2180 2246 2222 2243 2244 2283 2283 2283 2276 2266 2288 2197 2261 2288 -91 0.960 DejaVu Sans Mono 1747 2038 2159 2178 2157 2258 2250 2259 2278 2270 2273 2274 2285 2283 2281 2288 2280 2285 2287 -21 0.990 DialogInput 1664 1954 2093 2089 2100 2177 2230 2268 2277 2273 2274 2280 2277 2283 2287 2286 2280 2281 2288 -7 0.997 Droid Sans Mono 1119 2092 2119 2136 2095 2178 2167 2207 2193 2265 2282 2264 2282 2288 2288 2288 2288 2288 2288 -41 0.981 Droid Sans Mono Dotted 1743 2089 2118 2136 2095 2178 2167 2207 2193 2265 2282 2264 2282 2288 2288 2288 2288 2288 2288 -41 0.981 Droid Sans Mono Slashed 1618 2087 2119 2136 2095 2178 2085 2207 2193 2265 2282 2264 2282 2288 2288 2288 2288 2288 2288 -93 0.957 FS Gothic 46 616 625 1920 1725 2023 2046 2112 2100 2194 2221 2232 2253 2264 2258 2265 2251 2280 2272 -195 0.898 FS Mincho 132 742 0 1928 1013 1988 1950 1804 2139 2089 2168 2243 2253 2213 2236 2237 2204 2228 2226 -915 0.000 FreeMono 109 929 1179 2082 2063 2120 1966 2050 2149 2248 2230 2250 2269 2281 2273 2288 2287 2288 2288 -154 0.927 GNU Unifont 889 1276 631 1988 2196 2148 2180 2234 2245 2253 2248 2277 2271 2286 2281 2283 2285 2288 2287 -645 0.495 Kochi Gothic 138 790 1367 922 1912 2045 1821 2186 2159 2207 1994 2220 2246 2240 2239 2258 2099 2194 2274 -445 0.674 Kochi Mincho 0 119 1232 1513 1732 1853 0 1461 1271 1803 2032 2175 2210 2233 2049 2244 2230 2011 2165 -1853 0.000 Liberation Mono 1629 1554 2185 2156 2205 2180 2246 2222 2243 2244 2283 2283 2283 2276 2266 2288 2197 2261 2288 -91 0.954 Lucida Sans Typewriter Regular 1664 1954 2093 2089 2100 2177 2230 2268 2277 2273 2274 2280 2277 2283 2287 2286 2280 2281 2288 -7 0.997 Luxi Mono Regular 1103 1776 2030 2166 2180 2166 2185 2193 2243 2274 2273 2282 2284 2282 2275 2263 2281 2284 2288 -21 0.991 M+ 1m light 1866 2045 2130 2190 2208 2257 2245 2261 2277 2278 2280 2287 2287 2287 2281 2245 2278 2275 2282 -42 0.982 M+ 1m medium 1641 2089 2163 2215 2123 2216 2227 2254 2228 2277 2263 2287 2287 2288 2288 2288 2288 2288 2288 -92 0.958 M+ 1m regular 1897 2132 2190 2185 2149 2244 2260 2264 2275 2284 2267 2287 2287 2288 2288 2282 2277 2284 2276 -41 0.981 M+ 1m thin 1415 1969 1883 2093 1943 2144 2204 2211 2166 2254 2230 2262 2287 2287 2281 2258 2261 2269 2263 -150 0.928 M+ 1mn light 1921 2144 2120 2166 2213 2243 2240 2260 2280 2277 2273 2286 2284 2287 2287 2275 2280 2285 2261 -26 0.989 M+ 1mn medium 1889 2172 2129 2215 2159 2222 2233 2257 2232 2277 2258 2286 2288 2288 2288 2288 2288 2288 2288 -56 0.975 M+ 1mn regular 1849 2158 2148 2171 2178 2217 2256 2262 2281 2283 2263 2286 2284 2288 2286 2280 2267 2271 2282 -21 0.991 M+ 1mn thin 1201 1981 1875 1712 1911 2142 2204 2180 2157 2253 2234 2261 2284 2286 2286 2281 2286 2280 2275 -269 0.864 M+ 2m light 1877 2155 2120 2190 2207 2257 2246 2261 2277 2278 2279 2287 2287 2287 2281 2254 2287 2281 2282 -35 0.984 M+ 2m medium 1502 2089 2157 2217 2126 2210 2227 2259 2228 2277 2272 2287 2287 2288 2288 2288 2288 2288 2288 -91 0.959 M+ 2m regular 1898 2134 2192 2191 2150 2244 2260 2267 2281 2284 2267 2287 2287 2288 2288 2288 2288 2288 2267 -42 0.981 M+ 2m thin 1409 1968 1897 2095 1939 2144 2204 2211 2166 2254 2234 2262 2287 2287 2281 2252 2281 2283 2273 -156 0.926 MigMix 1M Regular 1888 2144 2189 2185 2167 2245 2260 2264 2275 2284 2267 2287 2287 2288 2288 2282 2277 2284 2276 -22 0.990 MigMix 2M Regular 1890 2146 2191 2191 2168 2245 2260 2267 2281 2284 2267 2287 2287 2288 2288 2288 2288 2288 2267 -23 0.990 Migu 1M Regular 0 1915 1501 2133 0 2161 2246 2251 2267 2240 2251 2282 2283 2287 2288 2266 2278 2273 2273 -2133 0.000 Migu 2M Regular 264 947 1742 2050 1866 2170 2246 2260 2267 2223 2251 2280 2283 2287 2288 2267 2282 2273 2275 -184 0.910 Ming(for ISO10646) 0 0 1505 1567 1045 1600 2050 2091 2148 2166 2259 2135 2254 2145 2233 2270 2237 2236 2179 -522 0.667 Mitra Mono 740 1856 1942 2071 2126 2178 2172 2152 2212 2246 2200 2259 2283 2260 2286 2287 2287 2288 2288 -46 0.980 Monospaced 1664 1954 2093 2089 2100 2177 2230 2268 2277 2273 2274 2280 2277 2283 2287 2286 2280 2281 2288 -7 0.997 Nimbus Mono L Regular 0 1649 1331 2124 2102 2100 2092 2064 2166 2226 2260 2268 2251 2279 2281 2288 2285 2288 2286 -318 0.807 Oxygen Mono 2163 2106 2169 2198 2237 2237 2238 2225 2276 2284 2285 2283 2285 2288 2288 2288 2271 2288 2288 -57 0.974 PT Mono 763 1668 2165 2155 2201 2186 1541 2265 2272 2265 2280 2282 2283 2288 2288 2288 2288 2287 2288 -660 0.700 Ricty Discord Regular 170 1112 2144 2200 2201 2250 2222 2232 2263 2251 2257 2280 2276 2283 2286 2286 2287 2288 2288 -28 0.988 Ricty Regular 224 370 2112 2173 2192 2118 2204 2199 2245 2252 2263 2278 2277 2285 1857 2284 2286 2288 2288 -428 0.813 Sazanami Gothic Regular 506 846 2061 2043 2129 2228 2237 2232 2098 2261 2280 2280 2287 2286 2287 2277 2287 2288 2287 -139 0.938 Sazanami Mincho Regular 184 1601 562 2080 1657 2164 2050 2033 2244 2181 2243 2270 2272 2262 2278 2260 2208 2258 2247 -1039 0.351 Source Code Pro 1406 2093 2171 2220 2166 2199 2221 2265 2256 2246 2286 2286 2281 2285 2288 2287 2285 2284 2285 -54 0.976 Source Code Pro Black 1942 1249 2022 2192 2208 2184 2227 2150 2195 2278 2259 2278 2272 2269 2281 2282 2287 2283 2288 -693 0.643 Source Code Pro ExtraLight 1702 0 15 24 2035 2142 2123 2190 2140 2226 2149 2274 2232 2287 2288 2284 2285 2277 2283 -1702 0.000 Source Code Pro Light 1812 1068 2070 2081 1871 2169 2159 2218 2244 2261 2283 2285 2274 2287 2288 2285 2283 2284 2268 -744 0.589 Source Code Pro Medium 1991 2047 2197 2213 2223 2176 2201 2245 2247 2242 2286 2286 2279 2286 2288 2286 2284 2285 2286 -47 0.979 Source Code Pro Semibold 1843 1974 2069 2211 2194 2175 2119 2238 2224 2227 2272 2287 2271 2284 2288 2286 2286 2285 2284 -92 0.958 Tlwg Mono 1831 1892 2046 2093 2035 2150 2108 2150 2205 2263 2250 2258 2281 2283 2287 2288 2288 2288 2288 -58 0.972 Tlwg Typewriter 1818 1893 2046 2091 2033 2157 2137 2107 2216 2263 2250 2264 2281 2283 2281 2288 2288 2288 2287 -58 0.972 Tlwg Typist 1982 2044 2131 2161 2133 2202 2208 2194 2262 2269 2270 2265 2282 2283 2287 2288 2288 2288 2288 -28 0.987 Tlwg Typo 1982 2044 2131 2161 2133 2202 2208 2194 2262 2269 2270 2265 2282 2283 2287 2288 2288 2288 2288 -28 0.987 Ubuntu Mono 115 949 1137 2090 2145 2165 2145 2195 2217 2221 2225 2258 2263 2274 2271 2282 2286 2287 2288 -20 0.991 Un Pilgia 1422 1386 1762 1910 1924 2146 2224 2212 2242 2226 2285 2277 2282 2279 2281 2282 2288 2281 2287 -36 0.975 Un Taza 1045 1873 2122 1823 2134 2114 2178 2193 2235 2224 2260 2270 2275 2281 2281 2279 2282 2264 2286 -299 0.859 VL Gothic Regular 1393 1905 2116 2068 2072 2230 2253 2263 2275 2280 2249 2284 2285 2288 2288 2283 2271 2276 2270 -48 0.977 Vn Nimbus Mono L 1909 2080 2172 2257 2231 2228 2249 2260 2262 2255 2266 2280 2256 2281 2284 2288 2288 2284 2288 -29 0.987 Vn cmsltl10 1813 2104 2060 2147 2173 2228 2252 2258 2117 2222 2270 2278 2288 2287 2288 2287 2287 2286 2288 -141 0.938 Vn cmtl10 1776 2091 1996 2177 2123 2223 2206 2258 2127 2226 2256 2277 2286 2277 2287 2287 2288 2286 2288 -131 0.942 WenQuanYi Micro Hei Mono 1743 2092 2119 2136 2095 2178 2183 2226 2193 2265 2282 2264 2282 2288 2288 2288 2288 2288 2288 -41 0.981 WenQuanYi Zen Hei Mono 1922 2174 2142 2172 2060 2223 2205 2263 2230 2284 2253 2287 2287 2288 2288 2284 2284 2288 2288 -114 0.948
