A study of textural changes is presented concerning the nematic phase of 4- n-alkyloxybenzoic acids (in particular, 4-n-heptyl- and 4-n-octyl-oxybenzoic acids), by means of a statistical approach to the image data observed by polarized light microscopy (orthoscopic mode). A new image processing method is developed in order to detect with high sensitivity any structural change in the image frame. To do this, a set of parameters is introduced, charaterizing the observed textures. Such a set is a vector, working like a pathfinder strongly increasing the human eye or in general the sensor skilfulness to appreciate any change of the optical texture, both in space and in time. This is suitable for revealing smooth transitions, such as phase transitions between smectic and nematic phases (or between different smectic phases), or order transitions, like alignment transitions in poorly oriented nematic layers. In fact, by using this method for detecting the order transition between two nematic 'subphases' of 4-n-alkyloxybenzoic acids, the sensitivity turns out to be enhanced by a factor higher than 10 with respect to that for standard techniques. The new method allows us to define a characteristic size of the image texture: this concept is applied to analyse several image data for estimating the mean size of the domains appearing in the smectic and in the nematic phase of the compounds under study.