State-of-the-art object-based approaches to automatic plant classification for crop/weed discrimination are reported to work with typical classification rates of 80–90% under laboratory or restricted field conditions. Adapting their parameter sets and classifiers to match changing field situation is laborious, yet it is required for practical application. Pixel-based classification allows adjusting the classifier model in the field easily by adding a few marks to sample data; however, pixel-based classification of camera data for crop/weed discrimination is impractical, as pixel features lack descriptiveness. This paper contributes a multi-wavelength laser line profile (MWLP) system for scanning the plants and obtaining sensor data, yielding image-based 3D range data, matched spectral reflectance, and scattering data at multiple wavelengths for each pixel. Using these descriptive pixel features, pixel-based Bayesian classification for crop/weed discrimination requires very few field-specific label data, thus allowing In-Field-Labeling for classifier adaptation to specific field situations. For different field situations and two different crops (carrots (Daucus carota) and corn salad (Valerianella locusta)) the classification using spectral and 3D features applying classifiers generated from very few marks in sample data (i.e., with very little effort for labeling), was successfully demonstrated, thereby achieving misclassification rates comparable to the best literature values.